# DeepSeek V4 Pro 0813Max > Source: Benchize (https://benchize.com) — https://benchize.com/models/deepseek-v4-pro-0813-max. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/deepseek-v4-pro-0813-max. DeepSeek Canonical URL: https://benchize.com/models/deepseek-v4-pro-0813-max Last updated: Wed, 21 Oct 2026 18:05:10 GMT Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations. DeepSeek ## Benchmarks | Benchmark | Score | ± | Rank | Cost | Latency | Source | | | --- | --- | --- | --- | --- | --- | --- | --- | | [HLAB-Vals-1.1 / structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Astructured_finance_securitization.md) | 0% | SE ±0 pp | 9 / 14 | $0.69 | 517.66source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.690061 \| USD \| per_test \| Lower is better \| \| `latency` \| 517.66 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/structured_finance_securitization/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [SWE-bench / overall](https://benchize.com/benchmarks/vals-ai%3Aswebench%3Aoverall.md) | 96.4% | SE ±0.83 pp | 2 / 39 | $0.1 | 240.41source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.4 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.103104 \| USD \| per_test \| Lower is better \| \| `latency` \| 240.413 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.83 pp sourcePopulation 88 stderr 0.834 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate litigation dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__litigation_dispute_resolution.md) | 85.39% | SE ±2.17 pp | 25 / 49 | $0.17 | 1,137.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.393 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.166693 \| USD \| per_test \| Lower is better \| \| `latency` \| 1137.476 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.17 pp sourcePopulation 81 stderr 2.165 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__litigation_dispute_resolution/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Ahealthcare_life_sciences.md) | 20% | SE ±20 pp | 5 / 14 | $0.74 | 581.14source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.741568 \| USD \| per_test \| Lower is better \| \| `latency` \| 581.14 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/healthcare_life_sciences/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [FrontierMath Tier 4 v2 (private)](https://benchize.com/benchmarks/epoch-ai%3Afrontiermath_tier_4_v2.md) | 26.83% | SE ±7.01 pp | 27 / 38 | — | — | [epoch ai · FrontierMath-Tier-4-v2-Private](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.2682926829268293 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.2682926829268293 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion FrontierMath-Tier-4-v2-Private reasoningBudget Not reported Reasoning effort max sourceModelVersion deepseek-v4-pro-0813_max ### Reported statistics Uncertainty Standard error: ±7.01 pp standardError 0.07005564203095158 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=frontiermath_tier_4_v2.csv) Source epoch ai Original model label deepseek-v4-pro-0813 Source version FrontierMath-Tier-4-v2-Private Evaluated 2026-08-19T13:35:48.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `48b886c828092231989fba6e3819efb7462e89ef681b7b306b4bfa3505829e4a` Source locator `/rows/25` | | | | | | | | | [Legal Research Bench / health](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Ahealth.md) | 60% | SE ±9.1 pp | 20 / 50 | $1.31 | 2,705.8source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.314815 \| USD \| per_test \| Lower is better \| \| `latency` \| 2705.795 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.1 pp sourcePopulation 82 stderr 9.097 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/health/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__emerging_companies_venture_capital.md) | 93.35% | SE ±1.46 pp | 7 / 14 | $0.82 | 618.82source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.345 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.819599 \| USD \| per_test \| Lower is better \| \| `latency` \| 618.824 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.46 pp sourcePopulation 24 stderr 1.459 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__emerging_companies_venture_capital/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [EMB / overall](https://benchize.com/benchmarks/vals-ai%3Aemb%3Aoverall.md) | 52.8% | SE ±3.06 pp | 37 / 47 | $1.08 | 2,247.24source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.803 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.08141 \| USD \| per_test \| Lower is better \| \| `latency` \| 2247.236 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.06 pp sourcePopulation 76 stderr 3.059 tokenTotals {"cache_read_tokens":855589504,"cache_write_tokens":null,"input_tokens":864870937,"output_tokens":15254147,"reasoning_tokens":11469965} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / energy natural resources](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aenergy_natural_resources.md) | 40% | SE ±24.5 pp | 3 / 14 | $0.98 | 548.64source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.979999 \| USD \| per_test \| Lower is better \| \| `latency` \| 548.636 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±24.5 pp sourcePopulation 24 stderr 24.495 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/energy_natural_resources/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [τ³-Banking](https://benchize.com/benchmarks/mercor%3Atau3-banking.md) | 40.2% | — | 15 / 24 | — | — | [mercor](https://www.mercor.com/apex/partner-benchmarks/tau-3-banking-leaderboard/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 40.2 \| percent \| task_completion_pass_at_1 \| Higher is better \| ### Configuration datasetUrl Not reported datasetVersion Not reported harness Not reported Reasoning effort max ### Reported statistics reportedErrors {"pass_1":8.1} sampleSize 291 ### Source [Original source](https://www.mercor.com/apex/partner-benchmarks/tau-3-banking-leaderboard/) Source mercor Original model label DeepSeek-V4-Pro-0813 Observed 2026-10-21T16:33:27.812Z Evidence SHA-256 `78850adeb8ad047fcb1dd65cc04ffaca61c86fc67e7035f9973805b02483ed07` Source locator `/__NEXT_DATA__/props/pageProps/leaderboard/rows/11` | | | | | | | | | [LegalBench / issue tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aissue_tasks.md) | 85.99% | SE ±0.66 pp | 30 / 44 | $0.00226 | 8.55source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.989 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002262 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.552 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.66 pp sourcePopulation 151 stderr 0.661 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/issue_tasks/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [IOI / overall](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aoverall.md) | 51.61% | SE ±2.4 pp | 18 / 29 | $2.15 | 4,045.97source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.611 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.151589 \| USD \| per_test \| Lower is better \| \| `latency` \| 4045.972 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.4 pp sourcePopulation 44 stderr 2.4 tokenTotals {"cache_read_tokens":126531285,"cache_write_tokens":0,"input_tokens":126847094,"output_tokens":1737645,"reasoning_tokens":1498891} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acorporate_ma.md) | 20% | SE ±20 pp | 1 / 49 | $0.14 | 1,088.1source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.144414 \| USD \| per_test \| Lower is better \| \| `latency` \| 1088.096 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 81 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/corporate_ma/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / corporate governance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acorporate_governance.md) | 0% | SE ±0 pp | 9 / 14 | $0.76 | 566.57source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.759983 \| USD \| per_test \| Lower is better \| \| `latency` \| 566.566 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/corporate_governance/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__trusts_estates_private_client.md) | 89.31% | SE ±1.91 pp | 9 / 49 | $0.16 | 1,292.3source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.313 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.163816 \| USD \| per_test \| Lower is better \| \| `latency` \| 1292.3 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.91 pp sourcePopulation 81 stderr 1.912 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__trusts_estates_private_client/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [LiveCodeBench / easy](https://benchize.com/benchmarks/vals-ai%3Alcb%3Aeasy.md) | 98.76% | SE ±0.62 pp | 14 / 43 | $0.0047 | 18.54source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 98.758 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004698 \| USD \| per_test \| Lower is better \| \| `latency` \| 18.54 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.62 pp sourcePopulation 143 stderr 0.617 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:14.220Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/easy/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__environmental_esg.md) | 89.79% | SE ±1.82 pp | 6 / 14 | $0.73 | 678.78source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.785 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.727139 \| USD \| per_test \| Lower is better \| \| `latency` \| 678.776 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.82 pp sourcePopulation 24 stderr 1.816 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__environmental_esg/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [EMB v1.1 / comps](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Acomps.md) | 59.31% | SE ±5.25 pp | 18 / 19 | $1.07 | 1,746.6source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.312 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.073792 \| USD \| per_test \| Lower is better \| \| `latency` \| 1746.604 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.25 pp sourcePopulation 30 stderr 5.247 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/comps/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [GPQA Diamond / diamond few shot cot](https://benchize.com/benchmarks/vals-ai%3Agpqa%3Adiamond_few_shot_cot.md) | 91.92% | SE ±3.02 pp | 12 / 40 | $0.06 | 278.28source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.919 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.061962 \| USD \| per_test \| Lower is better \| \| `latency` \| 278.283 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.02 pp sourcePopulation 138 stderr 3.024 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:06.040Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/diamond_few_shot_cot/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__data_privacy_cybersecurity.md) | 96.47% | SE ±1.1 pp | 8 / 14 | $0.8 | 532.25source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.466 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.795228 \| USD \| per_test \| Lower is better \| \| `latency` \| 532.25 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.1 pp sourcePopulation 24 stderr 1.099 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__data_privacy_cybersecurity/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Finance Agent (v2) / general qualitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Ageneral_qualitative_analysis.md) | 67.37% | SE ±0.45 pp | 18 / 50 | $0.92 | 862.66source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.367 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.915589 \| USD \| per_test \| Lower is better \| \| `latency` \| 862.657 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.45 pp sourcePopulation 80 stderr 0.446 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/general_qualitative_analysis/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Finance Agent (v2) / disclosure analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Adisclosure_analysis.md) | 59.85% | SE ±1.66 pp | 31 / 50 | $1.12 | 1,251.05source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.853 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.11808 \| USD \| per_test \| Lower is better \| \| `latency` \| 1251.051 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.66 pp sourcePopulation 80 stderr 1.663 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/disclosure_analysis/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [MMLU Pro / physics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aphysics.md) | 92.46% | SE ±0.73 pp | 17 / 40 | $0.01 | 71.37source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.456 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.014755 \| USD \| per_test \| Lower is better \| \| `latency` \| 71.374 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.73 pp sourcePopulation 138 stderr 0.733 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/physics/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [EMB v1.1 / dcf](https://benchize.com/benchmarks/vals-ai%3Aemb-v1-1%3Adcf.md) | 58.08% | SE ±6.33 pp | 17 / 19 | $0.99 | 2,340.58source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 58.083 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.986264 \| USD \| per_test \| Lower is better \| \| `latency` \| 2340.579 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.33 pp sourcePopulation 30 stderr 6.333 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb_v1_1.11L06J7L.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:55.456Z Evidence SHA-256 `eea2ef2c83a6dc7d553c7c6531c287710ea7ffbc56ee1ccec06c85b104b2408e` Source locator `/tasks/dcf/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Finance Agent (v2) / financial modeling](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Afinancial_modeling.md) | 16.84% | SE ±1.48 pp | 35 / 50 | $0.77 | 973.91source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 16.836 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.766127 \| USD \| per_test \| Lower is better \| \| `latency` \| 973.913 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.48 pp sourcePopulation 80 stderr 1.475 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/financial_modeling/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Chess Puzzles](https://benchize.com/benchmarks/epoch-ai%3Achess_puzzles.md) | 46% | SE ±5.01 pp | 20 / 63 | — | — | [epoch ai · Chess Puzzles](https://epoch.ai/data/benchmark_data.zip#file=chess_puzzles.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.46 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.46 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Chess Puzzles reasoningBudget Not reported Reasoning effort max sourceModelVersion deepseek-v4-pro-0813_max ### Reported statistics Uncertainty Standard error: ±5.01 pp standardError 0.05009082659620331 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=chess_puzzles.csv) Source epoch ai Original model label deepseek-v4-pro-0813 Source version Chess Puzzles Evaluated 2026-10-13T13:13:34.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `fa0a449c370b0cceaf273d9472078cce3e5aef6be7009bddf115e6df7f930c54` Source locator `/rows/132` | | | | | | | | | [LegalBench / interpretation tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Ainterpretation_tasks.md) | 77.55% | SE ±0.24 pp | 32 / 44 | $0.00345 | 15.49source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 77.552 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003453 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.491 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.24 pp sourcePopulation 151 stderr 0.237 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/interpretation_tasks/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aintellectual_property.md) | 0% | SE ±0 pp | 6 / 49 | $0.17 | 1,487.72source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.171603 \| USD \| per_test \| Lower is better \| \| `latency` \| 1487.716 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/intellectual_property/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aoverall.md) | 10.83% | SE ±2.72 pp | 7 / 14 | $0.8 | 655.41source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 10.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.802111 \| USD \| per_test \| Lower is better \| \| `latency` \| 655.413 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.72 pp sourcePopulation 24 stderr 2.723 tokenTotals {"cache_read_tokens":726363264,"cache_write_tokens":null,"input_tokens":746916941,"output_tokens":9384470,"reasoning_tokens":4362757} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / overall](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aoverall.md) | 7.5% | SE ±2.15 pp | 16 / 49 | $0.17 | 1,313.32source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 7.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.166206 \| USD \| per_test \| Lower is better \| \| `latency` \| 1313.321 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.15 pp sourcePopulation 81 stderr 2.148 tokenTotals {"cache_read_tokens":785343488,"cache_write_tokens":null,"input_tokens":805739429,"output_tokens":9454727,"reasoning_tokens":4381477} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [SRE Bench / overall](https://benchize.com/benchmarks/vals-ai%3Asrebench%3Aoverall.md) | 1.91% | SE ±0.85 pp | 18 / 24 | $5.58 | 8,425.73source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 1.908 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.579756 \| USD \| per_test \| Lower is better \| \| `latency` \| 8425.728 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.85 pp sourcePopulation 35 stderr 0.847 tokenTotals {"cache_read_tokens":24649477248,"cache_write_tokens":null,"input_tokens":24734059435,"output_tokens":67088556,"reasoning_tokens":39595412} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sre_bench.Bd0uBJxH.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:15.724Z Evidence SHA-256 `a10b2c964f5878b0fc21c888703f311a5ef7d7a74fc3c529cab3ddd9fa474e2b` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acorporate_ma.md) | 20% | SE ±20 pp | 4 / 14 | $0.79 | 587.4source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.785052 \| USD \| per_test \| Lower is better \| \| `latency` \| 587.404 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/corporate_ma/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [LiveCodeBench / medium](https://benchize.com/benchmarks/vals-ai%3Alcb%3Amedium.md) | 89.82% | SE ±1.55 pp | 11 / 43 | $0.04 | 155.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.817 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.04141 \| USD \| per_test \| Lower is better \| \| `latency` \| 155.532 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.55 pp sourcePopulation 143 stderr 1.545 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:14.220Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/medium/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [SWE-bench / 1-4 hours](https://benchize.com/benchmarks/vals-ai%3Aswebench%3A1-4%20hours.md) | 100% | SE ±0 pp | 1 / 39 | $0.16 | 305.02source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 100 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.161067 \| USD \| per_test \| Lower is better \| \| `latency` \| 305.017 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 88 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_swebench.Ae8ni7h0.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:13.711Z Evidence SHA-256 `7a4e2e8485283caac500127419f68ec4bd5414c837ade114fc6afa5b2d34ccaa` Source locator `/tasks/1-4 hours/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [ProgramBench / partial](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Apartial.md) | 70.1% | SE ±1.87 pp | 20 / 40 | $0.43 | 4,970.28source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.103 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.431698 \| USD \| per_test \| Lower is better \| \| `latency` \| 4970.276 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.87 pp sourcePopulation 64 stderr 1.87 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/partial/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [CyberBench v1.1 / overall](https://benchize.com/benchmarks/benchmark%3Acyber%3Aoverall.md) | 72.86% | SE ±5.5 pp | 10 / 28 | $0.59 | 1,353.19source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.857 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.593028 \| USD \| per_test \| Lower is better \| \| `latency` \| 1353.188 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.5 pp sourcePopulation 47 stderr 5.5 tokenTotals {"cache_read_tokens":490223040,"cache_write_tokens":null,"input_tokens":494905048,"output_tokens":1832767,"reasoning_tokens":1144956} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [LegalBench / overall](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aoverall.md) | 82.36% | SE ±0.44 pp | 26 / 44 | $0.00408 | 20.05source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.361 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004081 \| USD \| per_test \| Lower is better \| \| `latency` \| 20.049 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.44 pp sourcePopulation 151 stderr 0.437 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / immigration](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aimmigration.md) | 20% | SE ±20 pp | 2 / 14 | $0.53 | 483.41source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.526006 \| USD \| per_test \| Lower is better \| \| `latency` \| 483.414 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/immigration/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [IOI / ioi2025](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2025.md) | 48.5% | SE ±14.04 pp | 18 / 29 | $2.62 | 6,167.41source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.620016 \| USD \| per_test \| Lower is better \| \| `latency` \| 6167.407 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±14.04 pp sourcePopulation 44 stderr 14.041 tokenTotals {"cache_read_tokens":161448832,"cache_write_tokens":0,"input_tokens":161838645,"output_tokens":2026899,"reasoning_tokens":1719775} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Finance Agent (v2) / earnings analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aearnings_analysis.md) | 66.46% | SE ±3.25 pp | 34 / 50 | $0.33 | 635.73source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.463 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.327246 \| USD \| per_test \| Lower is better \| \| `latency` \| 635.73 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.25 pp sourcePopulation 80 stderr 3.249 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/earnings_analysis/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Terminal-Bench-Science / mathematical sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Amathematical_sciences.md) | 5.88% | SE ±5.88 pp | 15 / 30 | — | — | [Vals AI · 0.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 5.882 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Mini-SWE-agent maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.88 pp sourcePopulation 41 stderr 5.882 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/mathematical_sciences/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [SkillsBench / with skills](https://benchize.com/benchmarks/vals-ai%3Askillsbench%3Awith_skills.md) | 53.83% | SE ±4.49 pp | 12 / 20 | $0.37 | 674.65source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 53.829 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.374596 \| USD \| per_test \| Lower is better \| \| `latency` \| 674.652 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.49 pp sourcePopulation 35 stderr 4.49 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:11.147Z Evidence SHA-256 `aaad242949d81b7c7c61c36d4895d4460e9146760c1e6b4b38d235a16043bc61` Source locator `/tasks/with_skills/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aenvironmental_esg.md) | 0% | SE ±0 pp | 1 / 49 | $0.17 | 1,796.95source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.168238 \| USD \| per_test \| Lower is better \| \| `latency` \| 1796.954 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/environmental_esg/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Legal Research Bench / business commercial](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Abusiness_commercial.md) | 34.88% | SE ±7.35 pp | 25 / 50 | $1.03 | 2,499.93source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 34.884 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.025341 \| USD \| per_test \| Lower is better \| \| `latency` \| 2499.931 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.35 pp sourcePopulation 82 stderr 7.354 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/business_commercial/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Tax Agent Bench / current temporal analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Acurrent_temporal_analysis.md) | 43.56% | SE ±8.78 pp | 13 / 46 | $0.95 | 2,180.11source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.556 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.952634 \| USD \| per_test \| Lower is better \| \| `latency` \| 2180.108 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.78 pp sourcePopulation 73 stderr 8.784 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/current_temporal_analysis/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [APEX-Agents](https://benchize.com/benchmarks/mercor%3Aapex-agents%3A1.1.md) | 47.3% | — | 24 / 38 | — | — | [mercor · 1.1](https://www.mercor.com/apex/apex-agents-leaderboard/) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 47.3 \| percent \| task_completion_pass_at_1 \| Higher is better \| \| `mean_score` \| 62.3 \| percent \| rubric_mean \| Higher is better \| ### Configuration datasetUrl https://huggingface.co/datasets/mercor/apex-agents-v1.1 datasetVersion 1.1 harness loop_truncated_tools_agent Reasoning effort max ### Reported statistics reportedErrors {"mean_score":4.9,"pass_1":5.6} sampleSize 849 ### Source [Original source](https://www.mercor.com/apex/apex-agents-leaderboard/) Source mercor Original model label DeepSeek-V4-Pro-0813 Source version 1.1 Observed 2026-10-21T16:33:27.509Z Evidence SHA-256 `359c569c3b0b62ab375895eabf3c45846fa45551d419d5c9d6a4c9117db78184` Source locator `/__NEXT_DATA__/props/pageProps/leaderboardData/18` | | | | | | | | | [Terminal-Bench-Science / engineering sciences](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aengineering_sciences.md) | 0% | SE ±0 pp | 12 / 30 | — | — | [Vals AI · 0.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Mini-SWE-agent maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 41 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/engineering_sciences/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [CyberBench v1.1 / patch](https://benchize.com/benchmarks/benchmark%3Acyber%3Apatch.md) | 85.71% | SE ±4.68 pp | 11 / 28 | $0.29 | 752.16source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.714 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.286927 \| USD \| per_test \| Lower is better \| \| `latency` \| 752.164 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.68 pp sourcePopulation 47 stderr 4.676 tokenTotals {"cache_read_tokens":161342336,"cache_write_tokens":null,"input_tokens":164763464,"output_tokens":1124488,"reasoning_tokens":772476} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/patch/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [MMLU Pro / economics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aeconomics.md) | 89.22% | SE ±1.09 pp | 22 / 40 | $0.00767 | 38.28source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.218 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007669 \| USD \| per_test \| Lower is better \| \| `latency` \| 38.278 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.09 pp sourcePopulation 138 stderr 1.088 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/economics/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,936.4 | Range 1,893.5–1,973 | 42 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1936.4 \| rating \| reported \| Higher is better \| \| `overall` \| 80.12 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 67.93 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 80.17 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 77.58 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 80.89 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 93.38 \| source_score \| rubric \| Higher is better \| \| `slop` \| 81.42 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 94.91 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 81.74 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 76.32 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 76.46 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 78.86 \| source_score \| rubric \| Higher is better \| ### Configuration provider openrouter Reasoning effort max scoreScope 10_task_current sourceConfiguration deepseek-v4-pro-0813-max-or thinkingEnabled true ### Reported statistics Uncertainty Reported interval: 1,893.5–1,973 interval [1893.5,1973] rank 42 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label DeepSeek V4 Pro 0813 (max) Evaluated 2026-10-10 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/41` | | | | | | | | | [Legal Research Bench / weighted pass immigration](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__immigration.md) | 80.66% | SE ±7.6 pp | 18 / 50 | $1.32 | 2,999.17source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.657 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.324131 \| USD \| per_test \| Lower is better \| \| `latency` \| 2999.169 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.6 pp sourcePopulation 82 stderr 7.595 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__immigration/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [LegalBench / rule tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arule_tasks.md) | 78.98% | SE ±1.56 pp | 26 / 44 | $0.00951 | 51.49source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.978 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009512 \| USD \| per_test \| Lower is better \| \| `latency` \| 51.492 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.56 pp sourcePopulation 151 stderr 1.556 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/rule_tasks/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Code Migration / cli](https://benchize.com/benchmarks/vals-ai%3Acode-migration%3Acli.md) | 32.05% | SE ±2.64 pp | 23 / 47 | $23.9 | 14,905.26source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 32.053 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 23.900294 \| USD \| per_test \| Lower is better \| \| `latency` \| 14905.255 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.64 pp sourcePopulation 79 stderr 2.637 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:12.712Z Evidence SHA-256 `99194597f2c76c402195be47839409046e18bd30454616da6dd40b736a088fa4` Source locator `/tasks/cli/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__emerging_companies_venture_capital.md) | 90.44% | SE ±1.72 pp | 12 / 49 | $0.18 | 1,442.67source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.444 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.175319 \| USD \| per_test \| Lower is better \| \| `latency` \| 1442.672 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.72 pp sourcePopulation 81 stderr 1.72 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__emerging_companies_venture_capital/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Abankruptcy_restructuring.md) | 0% | SE ±0 pp | 3 / 49 | $0.19 | 1,383.64source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.186039 \| USD \| per_test \| Lower is better \| \| `latency` \| 1383.638 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/bankruptcy_restructuring/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Astructured_finance_securitization.md) | 0% | SE ±0 pp | 12 / 49 | $0.16 | 1,320.05source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.163846 \| USD \| per_test \| Lower is better \| \| `latency` \| 1320.054 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/structured_finance_securitization/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate energy natural resources](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__energy_natural_resources.md) | 96.7% | SE ±1.03 pp | 3 / 49 | $0.22 | 1,538.62source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 96.7 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.224328 \| USD \| per_test \| Lower is better \| \| `latency` \| 1538.616 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.03 pp sourcePopulation 81 stderr 1.028 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__energy_natural_resources/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate funds asset management](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__funds_asset_management.md) | 82.22% | SE ±2.07 pp | 21 / 49 | $0.22 | 1,677.15source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.216 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.219769 \| USD \| per_test \| Lower is better \| \| `latency` \| 1677.146 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.07 pp sourcePopulation 81 stderr 2.068 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__funds_asset_management/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Code Migration v1.1 / cli](https://benchize.com/benchmarks/vals-ai%3Acode-migration-v1-1%3Acli.md) | 36.82% | SE ±2.9 pp | 12 / 17 | $15.15 | 12,201.59source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 36.815 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 15.150147 \| USD \| per_test \| Lower is better \| \| `latency` \| 12201.593 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.9 pp sourcePopulation 26 stderr 2.904 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:46:09.631Z Evidence SHA-256 `352faac603c73f05cc01e89214fb4adcafa05ea7432ea71ea9903a6b5fe36b08` Source locator `/tasks/cli/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Terminal-Bench 4.0 / media](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-4%3Amedia.md) | 0% | SE ±0 pp | 24 / 36 | — | — | [Vals AI · 4.0](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 52 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_4.CAnGyzC_.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 4.0 Observed 2026-10-21T16:46:10.642Z Evidence SHA-256 `98f6964580e901f1aa143db664bd92aa558415f643569492545d67c47d7f519b` Source locator `/tasks/media/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate environmental esg](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__environmental_esg.md) | 83.51% | SE ±2.23 pp | 22 / 49 | $0.17 | 1,796.95source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.513 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.168238 \| USD \| per_test \| Lower is better \| \| `latency` \| 1796.954 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.23 pp sourcePopulation 81 stderr 2.226 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__environmental_esg/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / funds asset management](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Afunds_asset_management.md) | 20% | SE ±20 pp | 4 / 14 | $1.08 | 727.48source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.084471 \| USD \| per_test \| Lower is better \| \| `latency` \| 727.476 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 24 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/funds_asset_management/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / real estate](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Areal_estate.md) | 0% | SE ±0 pp | 6 / 49 | $0.2 | 1,536source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.19941 \| USD \| per_test \| Lower is better \| \| `latency` \| 1535.996 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/real_estate/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Legal Research Bench / family](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Afamily.md) | 22.73% | SE ±9.15 pp | 13 / 50 | $1.54 | 3,456.12source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 22.727 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.536833 \| USD \| per_test \| Lower is better \| \| `latency` \| 3456.123 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.15 pp sourcePopulation 82 stderr 9.145 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/family/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Finance Agent (v2) / adjustments](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aadjustments.md) | 48.8% | SE ±1.16 pp | 26 / 50 | $0.94 | 1,056.94source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.801 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.943878 \| USD \| per_test \| Lower is better \| \| `latency` \| 1056.943 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.16 pp sourcePopulation 80 stderr 1.156 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/adjustments/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [MMLU Pro / history](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Ahistory.md) | 78.48% | SE ±2.12 pp | 20 / 40 | $0.00659 | 36.3source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 78.478 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006593 \| USD \| per_test \| Lower is better \| \| `latency` \| 36.299 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.12 pp sourcePopulation 138 stderr 2.115 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/history/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Vals Index / tax agent bench](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Atax_agent_bench.md) | 26.76% | SE ±3.09 pp | 11 / 14 | $0.73 | 1,596.76source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 26.756 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.729136 \| USD \| per_test \| Lower is better \| \| `latency` \| 1596.755 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.09 pp sourcePopulation 23 stderr 3.093 tokenTotals {"cache_read_tokens":133313152,"cache_write_tokens":null,"input_tokens":172298347,"output_tokens":21059828,"reasoning_tokens":17608474} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/tax_agent_bench/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [CorpFin v2 / max fitting context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Amax_fitting_context.md) | 66.2% | SE ±1.62 pp | 14 / 39 | $0.00264 | 34.41source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.2 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002636 \| USD \| per_test \| Lower is better \| \| `latency` \| 34.411 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.62 pp sourcePopulation 134 stderr 1.615 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:45:57.998Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/max_fitting_context/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Mystery Game Puzzles](https://benchize.com/benchmarks/epoch-ai%3Amystery_game_puzzles.md) | 43% | SE ±4.98 pp | 14 / 71 | — | — | [epoch ai · Mystery Game Puzzles](https://epoch.ai/data/benchmark_data.zip#file=mystery_game_puzzles.csv) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.43 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.43 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Mystery Game Puzzles reasoningBudget Not reported Reasoning effort max sourceModelVersion deepseek-v4-pro-0813_max ### Reported statistics Uncertainty Standard error: ±4.98 pp standardError 0.0497569851956243 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=mystery_game_puzzles.csv) Source epoch ai Original model label deepseek-v4-pro-0813 Source version Mystery Game Puzzles Evaluated 2026-08-19T18:14:49.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `795b977bc82c460a5e2c1d6dd7b2569ddb21853f3829c4f6fdd16edfaf47bfcf` Source locator `/rows/92` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aemerging_companies_venture_capital.md) | 20% | SE ±20 pp | 6 / 49 | $0.18 | 1,442.67source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.175319 \| USD \| per_test \| Lower is better \| \| `latency` \| 1442.672 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±20 pp sourcePopulation 81 stderr 20 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/emerging_companies_venture_capital/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / antitrust competition](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Aantitrust_competition.md) | 0% | SE ±0 pp | 8 / 14 | $0.76 | 654.15source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.759752 \| USD \| per_test \| Lower is better \| \| `latency` \| 654.154 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/antitrust_competition/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate banking finance](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__banking_finance.md) | 93.66% | SE ±1.49 pp | 4 / 14 | $0.76 | 751.41source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 93.657 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.76189 \| USD \| per_test \| Lower is better \| \| `latency` \| 751.412 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.49 pp sourcePopulation 24 stderr 1.492 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__banking_finance/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__international_trade_sanctions.md) | 90.64% | SE ±1.84 pp | 10 / 14 | $0.64 | 639.65source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.637 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.64046 \| USD \| per_test \| Lower is better \| \| `latency` \| 639.65 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.84 pp sourcePopulation 24 stderr 1.842 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__international_trade_sanctions/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Finance Agent (v2) / overall](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Aoverall.md) | 50.39% | SE ±0.25 pp | 32 / 50 | $0.88 | 974.52source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.393 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.880465 \| USD \| per_test \| Lower is better \| \| `latency` \| 974.518 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.25 pp sourcePopulation 80 stderr 0.249 tokenTotals {"cache_read_tokens":218761173,"cache_write_tokens":null,"input_tokens":419761736,"output_tokens":30621918,"reasoning_tokens":25089786} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [SkillsBench / no skills](https://benchize.com/benchmarks/vals-ai%3Askillsbench%3Ano_skills.md) | 42.06% | SE ±4.36 pp | 11 / 20 | $0.42 | 794.41source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42.056 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.423503 \| USD \| per_test \| Lower is better \| \| `latency` \| 794.407 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness OpenHands maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.36 pp sourcePopulation 35 stderr 4.364 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_skillsbench.BE2TXB-M.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:11.147Z Evidence SHA-256 `aaad242949d81b7c7c61c36d4895d4460e9146760c1e6b4b38d235a16043bc61` Source locator `/tasks/no_skills/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate data privacy cybersecurity](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__data_privacy_cybersecurity.md) | 92.93% | SE ±1.53 pp | 20 / 49 | $0.16 | 1,108.12source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.933 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.161869 \| USD \| per_test \| Lower is better \| \| `latency` \| 1108.122 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.53 pp sourcePopulation 81 stderr 1.526 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__data_privacy_cybersecurity/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [MMLU Pro / computer science](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Acomputer_science.md) | 90% | SE ±1.59 pp | 17 / 40 | $0.01 | 46.18source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.011516 \| USD \| per_test \| Lower is better \| \| `latency` \| 46.177 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.59 pp sourcePopulation 138 stderr 1.588 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/computer_science/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate energy natural resources](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__energy_natural_resources.md) | 97.86% | SE ±0.83 pp | 4 / 14 | $0.98 | 548.64source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 97.855 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.979999 \| USD \| per_test \| Lower is better \| \| `latency` \| 548.636 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.83 pp sourcePopulation 24 stderr 0.834 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__energy_natural_resources/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Legal Research Bench / criminal](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Acriminal.md) | 35.09% | SE ±6.38 pp | 19 / 50 | $1.02 | 2,498.94source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.088 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.017486 \| USD \| per_test \| Lower is better \| \| `latency` \| 2498.94 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.38 pp sourcePopulation 82 stderr 6.377 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/criminal/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Vals Index / code migration](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Acode_migration.md) | 52.03% | SE ±3.36 pp | 8 / 14 | $11.81 | 10,883.53source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.028 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.806673 \| USD \| per_test \| Lower is better \| \| `latency` \| 10883.534 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.36 pp sourcePopulation 23 stderr 3.359 tokenTotals {"cache_read_tokens":14118838528,"cache_write_tokens":0,"input_tokens":14146599509,"output_tokens":27289057,"reasoning_tokens":11810197} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/code_migration/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [ProgramBench / overall](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Aoverall.md) | 0% | SE ±0 pp | 23 / 40 | $0.43 | 4,970.28source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.431698 \| USD \| per_test \| Lower is better \| \| `latency` \| 4970.276 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 64 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 61.25% | — | 66 / 212 | 0.6usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6125 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.5976109150000003 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup deepseek-v4-pro-0813 modelType CoT Reasoning effort max sourceModelVersion deepseek-v4-pro-0813-max thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label DeepSeek V4 Pro 0813 (Max) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/217` | | | | | | | | | [HLAB-Vals-1.1 / trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Atrusts_estates_private_client.md) | 0% | SE ±0 pp | 11 / 14 | $0.89 | 653.92source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.89094 \| USD \| per_test \| Lower is better \| \| `latency` \| 653.918 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 24 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/trusts_estates_private_client/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Legal Research Bench / weighted pass civil litigation](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__civil_litigation.md) | 85.79% | SE ±3.71 pp | 28 / 50 | $1.1 | 2,280.79source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.785 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.099633 \| USD \| per_test \| Lower is better \| \| `latency` \| 2280.787 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.71 pp sourcePopulation 82 stderr 3.712 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__civil_litigation/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / arbitration international dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aarbitration_international_dispute_resolution.md) | 0% | SE ±0 pp | 4 / 49 | $0.22 | 1,522.16source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.220117 \| USD \| per_test \| Lower is better \| \| `latency` \| 1522.162 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/arbitration_international_dispute_resolution/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Vals Index / legal agent benchmark](https://benchize.com/benchmarks/vals-ai%3Avals_index%3Alegal_agent_benchmark.md) | 10.83% | SE ±2.72 pp | 7 / 14 | $0.8 | 655.41source duration | [Vals AI · 2.2](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 10.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.802111 \| USD \| per_test \| Lower is better \| \| `latency` \| 655.413 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.72 pp sourcePopulation 23 stderr 2.723 tokenTotals {"cache_read_tokens":726363264,"cache_write_tokens":null,"input_tokens":746916941,"output_tokens":9384470,"reasoning_tokens":4362757} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_index.ye6C1wH2.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2.2 Observed 2026-10-21T16:45:49.430Z Evidence SHA-256 `0e95aee94cd2bf34bc4b43a8f4bb16c7817de138613c21011873fea4e0786b45` Source locator `/tasks/legal_agent_benchmark/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate intellectual property](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__intellectual_property.md) | 92.58% | SE ±1.56 pp | 11 / 49 | $0.17 | 1,487.72source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.58 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.171603 \| USD \| per_test \| Lower is better \| \| `latency` \| 1487.716 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.56 pp sourcePopulation 81 stderr 1.561 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__intellectual_property/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Terminal-Bench 2.1 / medium](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-2-1%3Amedium.md) | 67.27% | SE ±2.78 pp | 29 / 43 | $0.16 | 1,395.48source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.273 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.159222 \| USD \| per_test \| Lower is better \| \| `latency` \| 1395.478 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.78 pp sourcePopulation 76 stderr 2.777 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_2_1.CdyoObsA.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2.1 Observed 2026-10-21T16:46:13.216Z Evidence SHA-256 `a5306805cdf86495bdcceff6b2c8534a3768b9853f5077895dab975b809b054f` Source locator `/tasks/medium/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate white collar defense investigations](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__white_collar_defense_investigations.md) | 82.83% | SE ±2.19 pp | 24 / 49 | $0.15 | 1,069.22source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 82.828 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.148855 \| USD \| per_test \| Lower is better \| \| `latency` \| 1069.216 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.19 pp sourcePopulation 81 stderr 2.192 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__white_collar_defense_investigations/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Tax Agent Bench / controversy precedence analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Acontroversy_precedence_analysis.md) | 5.67% | SE ±4 pp | 31 / 46 | $0.82 | 1,814.3source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 5.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.816262 \| USD \| per_test \| Lower is better \| \| `latency` \| 1814.296 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4 pp sourcePopulation 73 stderr 4.002 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/controversy_precedence_analysis/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [MMLU Pro / engineering](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aengineering.md) | 83.39% | SE ±1.22 pp | 20 / 40 | $0.04 | 164.76source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.385 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.042054 \| USD \| per_test \| Lower is better \| \| `latency` \| 164.764 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.22 pp sourcePopulation 138 stderr 1.216 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/engineering/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [CorpFin v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aoverall.md) | 65.42% | SE ±0.94 pp | 12 / 39 | $0.00218 | 32.85source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.423 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002183 \| USD \| per_test \| Lower is better \| \| `latency` \| 32.854 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.94 pp sourcePopulation 134 stderr 0.937 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:45:57.998Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate real estate](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__real_estate.md) | 91.84% | SE ±1.48 pp | 17 / 49 | $0.2 | 1,536source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.837 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.19941 \| USD \| per_test \| Lower is better \| \| `latency` \| 1535.996 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.48 pp sourcePopulation 81 stderr 1.481 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__real_estate/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Finance Agent v2.1 / precedents](https://benchize.com/benchmarks/vals-ai%3Afabv2-1%3Aprecedents.md) | 30.71% | SE ±6.64 pp | 16 / 18 | $1.1 | 665.96source duration | [Vals AI · 2.1](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30.713 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.098715 \| USD \| per_test \| Lower is better \| \| `latency` \| 665.958 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.64 pp sourcePopulation 28 stderr 6.638 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2_1.ZbMhy9xo.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2.1 Observed 2026-10-21T16:45:54.954Z Evidence SHA-256 `f1b0c2d7dca4e73b52136862a9be059f7c8481c69f15d705ce90bf3bd9f78429` Source locator `/tasks/precedents/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Code Migration v1.1 / overall](https://benchize.com/benchmarks/vals-ai%3Acode-migration-v1-1%3Aoverall.md) | 51.99% | SE ±2.24 pp | 10 / 17 | $12.16 | 10,435.78source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.987 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 12.156614 \| USD \| per_test \| Lower is better \| \| `latency` \| 10435.782 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.24 pp sourcePopulation 26 stderr 2.235 tokenTotals {"cache_read_tokens":34096560384,"cache_write_tokens":0,"input_tokens":34168514159,"output_tokens":64280351,"reasoning_tokens":27684500} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration_v1_1.bJHk6HEY.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:46:09.631Z Evidence SHA-256 `352faac603c73f05cc01e89214fb4adcafa05ea7432ea71ea9903a6b5fe36b08` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / criteria pass rate insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__insurance.md) | 88.65% | SE ±1.92 pp | 16 / 49 | $0.12 | 986.99source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 88.645 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.11707 \| USD \| per_test \| Lower is better \| \| `latency` \| 986.986 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.92 pp sourcePopulation 81 stderr 1.924 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__insurance/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [TaxEval v2 / overall](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Aoverall.md) | 73.06% | SE ±0.87 pp | 22 / 40 | $0.05 | 226.3source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.058 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.045816 \| USD \| per_test \| Lower is better \| \| `latency` \| 226.296 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.87 pp sourcePopulation 145 stderr 0.872 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 2 Observed 2026-10-21T16:45:59.000Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/overall/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [HLAB-Vals-1.1 / criteria pass rate bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab%3Acriteria_pass_rate__bankruptcy_restructuring.md) | 89.45% | SE ±1.81 pp | 7 / 14 | $1 | 1,198.62source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 89.446 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.003903 \| USD \| per_test \| Lower is better \| \| `latency` \| 1198.624 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.81 pp sourcePopulation 24 stderr 1.81 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark.CFXFrRQl.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1.1 Observed 2026-10-21T16:45:52.890Z Evidence SHA-256 `14681f4a2310e0f257df9ec07c9c81e5dadc8f6f71634f02e174a02a8096d868` Source locator `/tasks/criteria_pass_rate__bankruptcy_restructuring/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [Harvey's Legal Agent Benchmark v1 / white collar defense investigations](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Awhite_collar_defense_investigations.md) | 0% | SE ±0 pp | 1 / 49 | $0.15 | 1,069.22source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.148855 \| USD \| per_test \| Lower is better \| \| `latency` \| 1069.216 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0 pp sourcePopulation 81 stderr 0 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/white_collar_defense_investigations/deepseek~1deepseek-v4-pro-0813` | | | | | | | | | [LiveCodeBench / hard](https://benchize.com/benchmarks/vals-ai%3Alcb%3Ahard.md) | 74% | SE ±2.35 pp | 11 / 43 | $0.15 | 645.63source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.14552 \| USD \| per_test \| Lower is better \| \| `latency` \| 645.626 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.35 pp sourcePopulation 143 stderr 2.345 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:46:14.220Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/hard/deepseek~1deepseek-v4-pro-0813` | | | | | | | | [Next page](https://benchize.com/models/deepseek-v4-pro-0813-max.md?cursor=64e66efb7fdd38a7d560f25b1392555a1e9e7de5b0a88221b23dbcc45cc41a41) --- Cite as: DeepSeek V4 Pro 0813Max — Benchize, https://benchize.com/models/deepseek-v4-pro-0813-max (retrieved 2026-10-21)