# Gemini 3.6 FlashHigh

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-3-6-flash-high. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-3-6-flash-high.

Google

Canonical URL: https://benchize.com/models/gemini-3-6-flash-high
Last updated: Wed, 21 Oct 2026 18:52:20 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Google

## Benchmarks

| Benchmark | Score | ± | Rank | Cost | Latency | Source |  |
| --- | --- | --- | --- | --- | --- | --- | --- |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__healthcare_life_sciences.md) | 87.13% | SE ±1.93 pp | 23 / 49 | $1.9 | 1,131.51source 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` \| 87.129 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.902096 \| USD \| per_test \| Lower is better \| \| `latency` \| 1131.514 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.93 pp sourcePopulation 81 stderr 1.927 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__healthcare_life_sciences/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text style control / expert](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aexpert.md) | 1,500.26 | — | 33 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1500.2602625806999 \| rating \| reported \| Higher is better \| ### Configuration category expert config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1490.669865980823 rank 41 upper 1509.850659180577 variance 23.94291107520232 votes 4212 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/2511/row` |  |  |  |  |  |  |  |
| [Arena text / industry legal and government](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_legal_and_government.md) | 1,479.3 | — | 28 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1479.2981252242555 \| rating \| reported \| Higher is better \| ### Configuration category industry_legal_and_government config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1468.0796163679302 rank 32 upper 1490.516634080581 variance 32.76227777881325 votes 3017 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5139/row` |  |  |  |  |  |  |  |
| [Legal Research Bench / weighted pass immigration](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__immigration.md) | 80.1% | SE ±7.35 pp | 21 / 50 | $0.41 | 147.17source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.097 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.405548 \| USD \| per_test \| Lower is better \| \| `latency` \| 147.165 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.35 pp sourcePopulation 82 stderr 7.353 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__immigration/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [GPQA Diamond / diamond few shot cot](https://benchize.com/benchmarks/vals-ai%3Agpqa%3Adiamond_few_shot_cot.md) | 92.42% | SE ±1.99 pp | 8 / 40 | $0.03 | 16.87source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.424 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.031197 \| USD \| per_test \| Lower is better \| \| `latency` \| 16.872 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.99 pp sourcePopulation 138 stderr 1.991 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_gpqa.ghZZBpyU.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:06.040Z Evidence SHA-256 `951eb5224097733a9d09d06c14908ae2980e2e640e539f2c284877c5092d7077` Source locator `/tasks/diamond_few_shot_cot/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Finance Agent (v2) / general quantitative analysis](https://benchize.com/benchmarks/vals-ai%3Afabv2%3Ageneral_quantitative_analysis.md) | 81.81% | SE ±0.82 pp | 2 / 50 | $1.57 | 642.21source 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` \| 81.808 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.573127 \| USD \| per_test \| Lower is better \| \| `latency` \| 642.213 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.82 pp sourcePopulation 80 stderr 0.821 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_finance_agent_v2.DypCOnwd.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 2 Observed 2026-10-21T16:45:57.035Z Evidence SHA-256 `f731b20a26c126725d125519f2b5841aa45254656dba859a9570d7ce7e5d8191` Source locator `/tasks/general_quantitative_analysis/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / insurance](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Ainsurance.md) | 0% | SE ±0 pp | 2 / 49 | $1.95 | 1,209.74source 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` \| 1.949242 \| USD \| per_test \| Lower is better \| \| `latency` \| 1209.736 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/insurance/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Tax Agent Bench / weighted pass current temporal analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__current_temporal_analysis.md) | 48.6% | SE ±8.56 pp | 36 / 46 | $0.4 | 132.73source 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` \| 48.604 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.396307 \| USD \| per_test \| Lower is better \| \| `latency` \| 132.729 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.56 pp sourcePopulation 73 stderr 8.557 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__current_temporal_analysis/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / overall](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Aoverall.md) | 65.08% | SE ±1.35 pp | 11 / 20 | $1.02 | 535.66source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.077 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.023831 \| USD \| per_test \| Lower is better \| \| `latency` \| 535.655 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.35 pp sourcePopulation 33 stderr 1.353 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/overall/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / international trade sanctions](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Ainternational_trade_sanctions.md) | 0% | SE ±0 pp | 4 / 49 | $1.59 | 857.59source 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` \| 1.591969 \| USD \| per_test \| Lower is better \| \| `latency` \| 857.59 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/international_trade_sanctions/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Legal Research Bench / administrative regulatory](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aadministrative_regulatory.md) | 31.82% | SE ±5.78 pp | 37 / 50 | $0.41 | 139.4source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 31.818 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.409841 \| USD \| per_test \| Lower is better \| \| `latency` \| 139.396 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.78 pp sourcePopulation 82 stderr 5.777 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/administrative_regulatory/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [CorpFin v2 / max fitting context](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Amax_fitting_context.md) | 65.39% | SE ±1.62 pp | 16 / 39 | $0.29 | 7.95source 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` \| 65.385 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.291436 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.954 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.62 pp sourcePopulation 134 stderr 1.624 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 2 Observed 2026-10-21T16:45:57.998Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/max_fitting_context/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [LegalBench / rhetoric tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Arhetoric_tasks.md) | 81.7% | SE ±1.1 pp | 15 / 44 | $0.00426 | 2.45source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.702 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004255 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.452 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.1 pp sourcePopulation 151 stderr 1.103 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/rhetoric_tasks/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [MMLU Pro / computer science](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Acomputer_science.md) | 91.71% | SE ±1.36 pp | 9 / 40 | $0.01 | 7.01source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.707 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.013111 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.006 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.36 pp sourcePopulation 138 stderr 1.362 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/computer_science/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [LegalBench / issue tasks](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aissue_tasks.md) | 91.12% | SE ±0.56 pp | 11 / 44 | $0.00511 | 2.52source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 91.121 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005112 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.519 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.56 pp sourcePopulation 151 stderr 0.557 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/issue_tasks/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [OTIS Mock AIME 2024–2025](https://benchize.com/benchmarks/epoch-ai%3Aotis_mock_aime_2024_2025.md) | 94.17% | SE ±3.09 pp | 36 / 123 | — | — | [epoch ai · OTIS Mock AIME 2024-2025](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9416666666666667 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.9416666666666667 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion OTIS Mock AIME 2024-2025 reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-3.6-flash_high ### Reported statistics Uncertainty Standard error: ±3.09 pp standardError 0.030926354359015452 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=otis_mock_aime_2024_2025.csv) Source epoch ai Original model label gemini-3.6-flash Source version OTIS Mock AIME 2024-2025 Evaluated 2026-08-02T00:21:27.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `5b411612f91e155dff4b09d09b548b42f7936482ea8b3c00b510bd46e2f6bc2c` Source locator `/rows/142` |  |  |  |  |  |  |  |
| [Tax Agent Bench / weighted pass numbers calculations](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__numbers_calculations.md) | 77.95% | SE ±6.59 pp | 17 / 46 | $0.31 | 94.18source 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` \| 77.948 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.306179 \| USD \| per_test \| Lower is better \| \| `latency` \| 94.184 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.59 pp sourcePopulation 73 stderr 6.587 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__numbers_calculations/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [LegalBench / overall](https://benchize.com/benchmarks/vals-ai%3Alegal_bench%3Aoverall.md) | 86.71% | SE ±0.41 pp | 10 / 44 | $0.00477 | 2.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 86.705 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004766 \| USD \| per_test \| Lower is better \| \| `latency` \| 2.962 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.41 pp sourcePopulation 151 stderr 0.414 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_bench.D6uTgA3b.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.390Z Evidence SHA-256 `c8486ba756baa5cd3955d035edff67440e8db23e69d62ad1a9e18d15b8c4bc52` Source locator `/tasks/overall/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [DeepSWE](https://benchize.com/benchmarks/deepswe%3Av1.1.md) | 46.68% | Range 42.98–50.39% | 53 / 70 | $4.42 | 1,477.86s | [deepswe](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_at_1` \| 0.4668141592920354 \| score_fraction \| scored_rollout_attempts \| Higher is better \| \| `pass_at_4` \| 0.7522123893805309 \| score_fraction \| tasks_with_one_passing_rollout \| Higher is better \| \| `cost_per_attempt` \| 4.419013277333334 \| USD \| scored_attempt \| Lower is better \| \| `duration` \| 1477.8607510707964 \| seconds \| scored_attempt \| Lower is better \| ### Configuration harness mini-swe-agent Reasoning effort high sourceConfiguration mini_swe_agent_gemini_3_6_flash_high ### Reported statistics Uncertainty Reported interval: 42.98–50.39% interval [0.4297656202995626,0.5038626982845081] intervalMethod 95% run-to-run: SE across repeated whole-benchmark passes (1.96 * std(runs)/sqrt(R)) runCount 4 sampleSize 452 taskCount 113 ### Source [Original source](https://deepswe.datacurve.ai/artifacts/v1.1/leaderboard-live.json) Source deepswe Original model label gemini-3-6-flash Observed 2026-10-21T16:30:23.371Z Evidence SHA-256 `a7c15d66288fd249c020b9931c017b92d1a3b90e480b3ff34974b752bd030019` Source locator `/rows/52` |  |  |  |  |  |  |  |
| [Mystery Game Puzzles](https://benchize.com/benchmarks/epoch-ai%3Amystery_game_puzzles.md) | 30% | SE ±4.61 pp | 27 / 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` \| 0.3 \| score_fraction \| Best score (across scorers) \| Higher is better \| \| `mean_score` \| 0.3 \| score_fraction \| mean_score \| Higher is better \| ### Configuration benchmarkVersion Mystery Game Puzzles reasoningBudget Not reported Reasoning effort high sourceModelVersion gemini-3.6-flash_high ### Reported statistics Uncertainty Standard error: ±4.61 pp standardError 0.04605661864718382 ### Source [Original source](https://epoch.ai/data/benchmark_data.zip#file=mystery_game_puzzles.csv) Source epoch ai Original model label gemini-3.6-flash Source version Mystery Game Puzzles Evaluated 2026-08-05T01:49:56.000Z Observed 2026-10-21T16:30:24.199Z Evidence SHA-256 `795b977bc82c460a5e2c1d6dd7b2569ddb21853f3829c4f6fdd16edfaf47bfcf` Source locator `/rows/117` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate employment labor](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__employment_labor.md) | 76.78% | SE ±2.59 pp | 30 / 49 | $1.8 | 1,131.37source 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` \| 76.779 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.795425 \| USD \| per_test \| Lower is better \| \| `latency` \| 1131.366 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.59 pp sourcePopulation 81 stderr 2.589 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__employment_labor/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [MortgageTax / semantic extraction](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Asemantic_extraction.md) | 58.43% | SE ±1.39 pp | 20 / 31 | $0.02 | 7.25source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 58.426 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.01573 \| USD \| per_test \| Lower is better \| \| `latency` \| 7.245 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.39 pp sourcePopulation 98 stderr 1.39 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:58.500Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/semantic_extraction/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [MMLU Pro / chemistry](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Achemistry.md) | 92.31% | SE ±0.79 pp | 12 / 40 | $0.02 | 9.27source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 92.314 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.018427 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.267 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.79 pp sourcePopulation 138 stderr 0.792 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/chemistry/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_business_and_management_and_financial_operations.md) | 1,464.4 | — | 25 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1464.3961996669793 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1456.6231378239725 rank 27 upper 1472.1692615099862 variance 15.728527425498447 votes 6833 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/4309/row` |  |  |  |  |  |  |  |
| [MMLU Pro / health](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Ahealth.md) | 84.6% | SE ±1.26 pp | 6 / 40 | $0.01 | 6.55source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 84.597 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010436 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.549 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.26 pp sourcePopulation 138 stderr 1.262 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/health/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena vision style control / overall](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aoverall.md) | 1,281.98 | — | 25 / 82 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1281.9847069492557 \| rating \| reported \| Higher is better \| ### Configuration category overall config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1274.089402916246 rank 26 upper 1289.8800109822657 variance 16.227123257928774 votes 8979 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/25/row` |  |  |  |  |  |  |  |
| [Arena text / expert](https://benchize.com/benchmarks/lmarena%3Atext%3Aexpert.md) | 1,489.72 | — | 30 / 148 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1489.718759424185 \| rating \| reported \| Higher is better \| ### Configuration category expert config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1480.1772785658247 rank 36 upper 1499.2602402825453 variance 23.69929269579017 votes 4212 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/2506/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_writing_and_literature_and_language.md) | 1,473.78 | — | 19 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473.7778432492792 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1466.710510227754 rank 20 upper 1480.8451762708044 variance 13.002142771405525 votes 9845 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/7137/row` |  |  |  |  |  |  |  |
| [ProgramBench / overall](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Aoverall.md) | 0% | SE ±0 pp | 23 / 40 | $5.92 | 2,852.75source 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` \| 5.923527 \| USD \| per_test \| Lower is better \| \| `latency` \| 2852.749 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/overall/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [BioMysteryBench / human solvable](https://benchize.com/benchmarks/vals-ai%3Abiomysterybench%3Ahuman_solvable.md) | 67.12% | SE ±2.85 pp | 20 / 20 | $1.13 | 761.96source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.123 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.130257 \| USD \| per_test \| Lower is better \| \| `latency` \| 761.958 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Terminus 2 maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.85 pp sourcePopulation 27 stderr 2.852 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_biomysterybench.Bley-WAP.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:04.029Z Evidence SHA-256 `59bf79d38ec415a34ffb1c2901a16ecbbe101b7fa864e86104d2571fc7cfc23d` Source locator `/tasks/human_solvable/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text / multi turn](https://benchize.com/benchmarks/lmarena%3Atext%3Amulti_turn.md) | 1,481.38 | — | 21 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1481.37781727395 \| rating \| reported \| Higher is better \| ### Configuration category multi_turn config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1472.9291163009093 rank 22 upper 1489.8265182469909 variance 18.581625227200263 votes 5787 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/9337/row` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / terminal bench 2 1](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Aterminal_bench_2_1.md) | 73.78% | SE ±1.63 pp | 8 / 20 | $1.17 | 552.15source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.783 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.174404 \| USD \| per_test \| Lower is better \| \| `latency` \| 552.153 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.63 pp sourcePopulation 33 stderr 1.633 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/terminal_bench_2_1/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Code Migration / code quality](https://benchize.com/benchmarks/vals-ai%3Acode-migration%3Acode_quality.md) | 3.3% | SE ±0.07 pp | 33 / 47 | $8.93 | 5,404.83source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 3.299 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.930416 \| USD \| per_test \| Lower is better \| \| `latency` \| 5404.829 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.07 pp sourcePopulation 79 stderr 0.073 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_code_migration.Dttzoqk3.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:12.712Z Evidence SHA-256 `99194597f2c76c402195be47839409046e18bd30454616da6dd40b736a088fa4` Source locator `/tasks/code_quality/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Tax Agent Bench / numbers calculations](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Anumbers_calculations.md) | 39.67% | SE ±9.03 pp | 22 / 46 | $0.31 | 94.18source 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` \| 39.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.306179 \| USD \| per_test \| Lower is better \| \| `latency` \| 94.184 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.03 pp sourcePopulation 73 stderr 9.027 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/numbers_calculations/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [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 | $2.14 | 906.2source 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` \| 2.137307 \| USD \| per_test \| Lower is better \| \| `latency` \| 906.196 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/white_collar_defense_investigations/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [CorpFin v2 / overall](https://benchize.com/benchmarks/vals-ai%3Acorp_fin_v2%3Aoverall.md) | 63.33% | SE ±0.95 pp | 19 / 39 | $0.14 | 6.33source 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` \| 63.326 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.136842 \| USD \| per_test \| Lower is better \| \| `latency` \| 6.329 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.95 pp sourcePopulation 134 stderr 0.949 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_corp_fin_v2.CectKwl1.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 2 Observed 2026-10-21T16:45:57.998Z Evidence SHA-256 `7cf2217ab3728d5a84bffce82aab9fc52d7f810b0cbe8c65b387df47f3d31c9b` Source locator `/tasks/overall/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [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 | $1.83 | 840.97source 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` \| 1.83107 \| USD \| per_test \| Lower is better \| \| `latency` \| 840.968 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/intellectual_property/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [EMB / comps](https://benchize.com/benchmarks/vals-ai%3Aemb%3Acomps.md) | 70.02% | SE ±3.84 pp | 16 / 47 | $4.73 | 603.57source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.019 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.730378 \| USD \| per_test \| Lower is better \| \| `latency` \| 603.567 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.84 pp sourcePopulation 76 stderr 3.84 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/comps/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text / korean](https://benchize.com/benchmarks/lmarena%3Atext%3Akorean.md) | 1,428.57 | — | 30 / 124 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1428.565137342548 \| rating \| reported \| Higher is better \| ### Configuration category korean config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1405.9432269698552 rank 36 upper 1451.1870477152409 variance 133.21783541016327 votes 707 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8269/row` |  |  |  |  |  |  |  |
| [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) | 83.84% | SE ±2.14 pp | 21 / 49 | $2.14 | 906.2source 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` \| 83.838 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.137307 \| USD \| per_test \| Lower is better \| \| `latency` \| 906.196 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.14 pp sourcePopulation 81 stderr 2.14 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__white_collar_defense_investigations/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Legal Research Bench / civil litigation](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Acivil_litigation.md) | 18.52% | SE ±7.62 pp | 38 / 50 | $0.48 | 192.42source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 18.519 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.477549 \| USD \| per_test \| Lower is better \| \| `latency` \| 192.418 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.62 pp sourcePopulation 82 stderr 7.618 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/civil_litigation/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [EMB / scratch](https://benchize.com/benchmarks/vals-ai%3Aemb%3Ascratch.md) | 65.69% | SE ±2.48 pp | 25 / 47 | $3.55 | 753.53source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.691 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.552764 \| USD \| per_test \| Lower is better \| \| `latency` \| 753.531 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.48 pp sourcePopulation 76 stderr 2.475 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/scratch/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / trusts estates private client](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Atrusts_estates_private_client.md) | 20% | SE ±20 pp | 2 / 49 | $2.03 | 985.07source 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` \| 2.033707 \| USD \| per_test \| Lower is better \| \| `latency` \| 985.068 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/trusts_estates_private_client/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [MMLU Pro / history](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Ahistory.md) | 83.47% | SE ±1.9 pp | 7 / 40 | $0.01 | 5.95source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 83.465 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.011323 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.946 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.9 pp sourcePopulation 138 stderr 1.903 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/history/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text style control / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_medicine_and_healthcare.md) | 1,480.14 | — | 35 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1480.1371031266 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1467.8214240157847 rank 57 upper 1492.4527822374155 variance 39.48394582378158 votes 2553 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/6369/row` |  |  |  |  |  |  |  |
| [EMB / misc](https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc.md) | 64.39% | SE ±3.01 pp | 15 / 47 | $2.63 | 583.67source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.394 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.630334 \| USD \| per_test \| Lower is better \| \| `latency` \| 583.672 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.01 pp sourcePopulation 76 stderr 3.006 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/misc/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Vals Multimodal Index / finance agent](https://benchize.com/benchmarks/vals-ai%3Avals_multimodal_index%3Afinance_agent.md) | 55.3% | SE ±1.29 pp | 7 / 20 | $1.39 | 295.32source duration | [Vals AI · 1.2](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.302 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.393912 \| USD \| per_test \| Lower is better \| \| `latency` \| 295.319 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.29 pp sourcePopulation 33 stderr 1.29 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_vals_multimodal_index.virVpWMs.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1.2 Observed 2026-10-21T16:45:51.881Z Evidence SHA-256 `077b22575f6e075b7b78157d000ec8f94d7ead409c7dcbcf04887630ed572a2d` Source locator `/tasks/finance_agent/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena vision style control / creative writing vision](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Acreative_writing_vision.md) | 1,261.24 | — | 30 / 70 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1261.2391546274118 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1239.0484585632312 rank 35 upper 1283.4298506915925 variance 128.18749719770915 votes 792 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/397/row` |  |  |  |  |  |  |  |
| [MortgageTax / overall](https://benchize.com/benchmarks/vals-ai%3Amortgage_tax%3Aoverall.md) | 67.61% | SE ±0.92 pp | 16 / 31 | $0.02 | 9.24source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.608 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.019658 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.239 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.92 pp sourcePopulation 98 stderr 0.915 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mortgage_tax.DCd-oO5Y.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:58.500Z Evidence SHA-256 `e5c844561f97d119d66d70269e726ecfb68be79eae39acf14ead3e95422e648c` Source locator `/tasks/overall/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [SAGE / linear algebra](https://benchize.com/benchmarks/vals-ai%3Asage%3Alinear_algebra.md) | 69.87% | SE ±5.14 pp | 13 / 41 | $0.04 | 18.15source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.867 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.042437 \| USD \| per_test \| Lower is better \| \| `latency` \| 18.148 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.14 pp sourcePopulation 91 stderr 5.138 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/linear_algebra/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [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) | 91.52% | SE ±1.66 pp | 24 / 49 | $1.88 | 1,096.26source 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` \| 91.519 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.875677 \| USD \| per_test \| Lower is better \| \| `latency` \| 1096.256 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.66 pp sourcePopulation 81 stderr 1.659 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__data_privacy_cybersecurity/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text / polish](https://benchize.com/benchmarks/lmarena%3Atext%3Apolish.md) | 1,473.45 | — | 19 / 117 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1473.4496119593944 \| rating \| reported \| Higher is better \| ### Configuration category polish config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1448.0709632731634 rank 23 upper 1498.828260645625 variance 167.6643793939565 votes 529 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/10170/row` |  |  |  |  |  |  |  |
| [MMLU Pro / economics](https://benchize.com/benchmarks/vals-ai%3Ammlu_pro%3Aeconomics.md) | 90.52% | SE ±1.01 pp | 15 / 40 | $0.00946 | 5.29source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.521 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009457 \| USD \| per_test \| Lower is better \| \| `latency` \| 5.287 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.01 pp sourcePopulation 138 stderr 1.008 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_mmlu_pro.y416pXDi.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:06.503Z Evidence SHA-256 `dab025507f46c716dd8d145e90ec0a737d9c56219853f41e4b1cc3c5e8c222b4` Source locator `/tasks/economics/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text style control / russian](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Arussian.md) | 1,492.9 | — | 19 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1492.900508566062 \| rating \| reported \| Higher is better \| ### Configuration category russian config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1483.1524256287048 rank 20 upper 1502.648591503419 variance 24.736727735227035 votes 4172 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10403/row` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / tax](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Atax.md) | 0% | SE ±0 pp | 3 / 49 | $1.48 | 1,063.3source 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` \| 0 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.480887 \| USD \| per_test \| Lower is better \| \| `latency` \| 1063.3 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/tax/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [CyberBench v1.1 / overall](https://benchize.com/benchmarks/benchmark%3Acyber%3Aoverall.md) | 45.36% | SE ±3.75 pp | 24 / 28 | $1.31 | 660.04source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.357 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.306182 \| USD \| per_test \| Lower is better \| \| `latency` \| 660.036 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.75 pp sourcePopulation 47 stderr 3.745 tokenTotals {"cache_read_tokens":243499364,"cache_write_tokens":null,"input_tokens":262805643,"output_tokens":1382568,"reasoning_tokens":850728} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/overall/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Legal Research Bench / overall](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aoverall.md) | 25% | SE ±3.01 pp | 37 / 50 | $0.47 | 168.48source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 25 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.466741 \| USD \| per_test \| Lower is better \| \| `latency` \| 168.482 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.01 pp sourcePopulation 82 stderr 3.01 tokenTotals {"cache_read_tokens":80852090,"cache_write_tokens":0,"input_tokens":116699947,"output_tokens":4157671,"reasoning_tokens":2875086} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/overall/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [ProgramBench / almost](https://benchize.com/benchmarks/vals-ai%3Aprogrambench%3Aalmost.md) | 2.5% | SE ±1.11 pp | 27 / 40 | $5.92 | 2,852.75source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 2.5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.923527 \| USD \| per_test \| Lower is better \| \| `latency` \| 2852.749 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.11 pp sourcePopulation 64 stderr 1.107 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_programbench.C_J7ZU4X.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:10.137Z Evidence SHA-256 `e9bbb4378c7a058441a21d456baf9316b96c2cf5b58d371a3c7c803f5000bd8c` Source locator `/tasks/almost/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / healthcare life sciences](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Ahealthcare_life_sciences.md) | 0% | SE ±0 pp | 24 / 49 | $1.9 | 1,131.51source 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` \| 1.902096 \| USD \| per_test \| Lower is better \| \| `latency` \| 1131.514 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/healthcare_life_sciences/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text style control / industry business and management and financial operations](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_business_and_management_and_financial_operations.md) | 1,472.91 | — | 32 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1472.9097119574885 \| rating \| reported \| Higher is better \| ### Configuration category industry_business_and_management_and_financial_operations config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1465.0601463927019 rank 38 upper 1480.7592775222752 variance 16.03965639927161 votes 6833 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/4320/row` |  |  |  |  |  |  |  |
| [Arena text style control / polish](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Apolish.md) | 1,471.92 | — | 29 / 117 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1471.918814145651 \| rating \| reported \| Higher is better \| ### Configuration category polish config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1446.6255028639089 rank 42 upper 1497.212125427393 variance 166.53870976013658 votes 529 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/10189/row` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate structured finance securitization](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__structured_finance_securitization.md) | 85.71% | SE ±1.98 pp | 11 / 49 | $1.69 | 870.67source 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` \| 85.714 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.692267 \| USD \| per_test \| Lower is better \| \| `latency` \| 870.666 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.98 pp sourcePopulation 81 stderr 1.975 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__structured_finance_securitization/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate.md) | 84.37% | SE ±0.44 pp | 26 / 49 | $1.9 | 984.49source 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` \| 84.368 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.895602 \| USD \| per_test \| Lower is better \| \| `latency` \| 984.49 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.44 pp sourcePopulation 81 stderr 0.437 tokenTotals {"cache_read_tokens":366081207,"cache_write_tokens":null,"input_tokens":434069662,"output_tokens":9410323,"reasoning_tokens":2894511} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_agent_benchmark_v1.ZWRzZKcv.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [SAGE / calculus](https://benchize.com/benchmarks/vals-ai%3Asage%3Acalculus.md) | 75.31% | SE ±5.76 pp | 13 / 36 | $0.05 | 15.15source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.309 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.047167 \| USD \| per_test \| Lower is better \| \| `latency` \| 15.152 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.76 pp sourcePopulation 91 stderr 5.764 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/calculus/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [CyberBench v1.1 / poc](https://benchize.com/benchmarks/benchmark%3Acyber%3Apoc.md) | 5% | SE ±2.81 pp | 24 / 28 | $1.35 | 595.99source duration | [Vals AI · 1.1](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 5 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.353677 \| USD \| per_test \| Lower is better \| \| `latency` \| 595.987 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.81 pp sourcePopulation 47 stderr 2.814 tokenTotals {"cache_read_tokens":332876499,"cache_write_tokens":null,"input_tokens":347255054,"output_tokens":1296179,"reasoning_tokens":482847} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_cyberbench.DS6UOlu0.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1.1 Observed 2026-10-21T16:46:15.238Z Evidence SHA-256 `943f593f929f8971a6b746269a2851b5febc2aad4e2f1066895f715033cdc7f1` Source locator `/tasks/poc/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / emerging companies venture capital](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Aemerging_companies_venture_capital.md) | 0% | SE ±0 pp | 18 / 49 | $1.88 | 1,159.89source 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` \| 1.881256 \| USD \| per_test \| Lower is better \| \| `latency` \| 1159.888 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/emerging_companies_venture_capital/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [TaxEval v2 / correctness](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Acorrectness.md) | 63.53% | SE ±1.38 pp | 15 / 40 | $0.02 | 12.34source 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` \| 63.532 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.020385 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.335 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.38 pp sourcePopulation 145 stderr 1.376 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 2 Observed 2026-10-21T16:45:59.000Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/correctness/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [IOI / ioi2025](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aioi2025.md) | 40.83% | SE ±9.71 pp | 22 / 29 | $1.75 | 935.62source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.747464 \| USD \| per_test \| Lower is better \| \| `latency` \| 935.617 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.71 pp sourcePopulation 44 stderr 9.711 tokenTotals {"cache_read_tokens":20352477,"cache_write_tokens":0,"input_tokens":22669003,"output_tokens":527617,"reasoning_tokens":382252} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/ioi2025/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,077.1 | Range 1,034.6–1,113.8 | 100 / 126 | — | — | [tonebench](https://benchmark.towardsai.com/data/leaderboard.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1077.1 \| rating \| reported \| Higher is better \| \| `overall` \| 69.16 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 59.96 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 69.82 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 71.75 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 72.37 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 85.9 \| source_score \| rubric \| Higher is better \| \| `slop` \| 73.4 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 86.84 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 71.44 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 58.27 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 65.79 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 69.99 \| source_score \| rubric \| Higher is better \| ### Configuration provider google Reasoning effort high scoreScope 10_task_current sourceConfiguration gemini-3-6-flash-high ### Reported statistics Uncertainty Reported interval: 1,034.6–1,113.8 interval [1034.6,1113.8] rank 104 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Gemini 3.6 Flash (high thinking) Evaluated 2026-10-11 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/103` |  |  |  |  |  |  |  |
| [Tax Agent Bench / weighted pass controversy precedence analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Aweighted_pass__controversy_precedence_analysis.md) | 37.36% | SE ±8.04 pp | 36 / 46 | $0.36 | 125.07source 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` \| 37.362 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.358641 \| USD \| per_test \| Lower is better \| \| `latency` \| 125.067 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.04 pp sourcePopulation 73 stderr 8.036 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/weighted_pass__controversy_precedence_analysis/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Tax Agent Bench / current temporal analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Acurrent_temporal_analysis.md) | 19.88% | SE ±7.38 pp | 36 / 46 | $0.4 | 132.73source 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` \| 19.875 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.396307 \| USD \| per_test \| Lower is better \| \| `latency` \| 132.729 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.38 pp sourcePopulation 73 stderr 7.382 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/current_temporal_analysis/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [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) | 88.12% | SE ±1.86 pp | 32 / 49 | $1.81 | 1,203.2source 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` \| 88.119 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.814778 \| USD \| per_test \| Lower is better \| \| `latency` \| 1203.204 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.86 pp sourcePopulation 81 stderr 1.862 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__energy_natural_resources/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text / industry medicine and healthcare](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_medicine_and_healthcare.md) | 1,468.75 | — | 26 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1468.7502211186948 \| rating \| reported \| Higher is better \| ### Configuration category industry_medicine_and_healthcare config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1456.575464702576 rank 38 upper 1480.924977534813 variance 38.58552198798126 votes 2553 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/6350/row` |  |  |  |  |  |  |  |
| [LiveCodeBench / medium](https://benchize.com/benchmarks/vals-ai%3Alcb%3Amedium.md) | 90.6% | SE ±1.49 pp | 5 / 43 | $0.04 | 25.17source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 90.601 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.044201 \| USD \| per_test \| Lower is better \| \| `latency` \| 25.172 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.49 pp sourcePopulation 143 stderr 1.491 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:14.220Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/medium/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [EMB / lbo](https://benchize.com/benchmarks/vals-ai%3Aemb%3Albo.md) | 52.47% | SE ±5.34 pp | 27 / 47 | $6.34 | 1,173.46source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.472 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.338788 \| USD \| per_test \| Lower is better \| \| `latency` \| 1173.459 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.34 pp sourcePopulation 76 stderr 5.339 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/lbo/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena vision style control / english](https://benchize.com/benchmarks/lmarena%3Avision_style_control%3Aenglish.md) | 1,275.97 | — | 26 / 82 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1275.9712083261234 \| rating \| reported \| Higher is better \| ### Configuration category english config vision_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1264.187986849049 rank 30 upper 1287.754429803198 variance 36.14364095999915 votes 3098 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `38568936995f36625aae49e9ea05557d55c1b1df9b2954f5c50cee523f26fe92` Source locator `/rows/619/row` |  |  |  |  |  |  |  |
| [Arena text style control / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Aindustry_life_and_physical_and_social_science.md) | 1,493.93 | — | 28 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1493.932226297393 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1485.663141455392 rank 32 upper 1502.2013111393942 variance 17.79994718565206 votes 5809 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/5529/row` |  |  |  |  |  |  |  |
| [Arena vision / english (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Aenglish--config-vision.md) | 1,294.79 | — | 17 / 82 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1294.7944069626483 \| rating \| reported \| Higher is better \| ### Configuration category english config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1283.082879517955 rank 19 upper 1306.505934407342 variance 35.70515303949624 votes 3098 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/608/row` |  |  |  |  |  |  |  |
| [LiveCodeBench / hard](https://benchize.com/benchmarks/vals-ai%3Alcb%3Ahard.md) | 74.57% | SE ±2.33 pp | 8 / 43 | $0.11 | 63.56source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.571 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.11252 \| USD \| per_test \| Lower is better \| \| `latency` \| 63.562 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.33 pp sourcePopulation 143 stderr 2.328 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_lcb.miyRUvVa.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:14.220Z Evidence SHA-256 `1a7c7dabc9d95a0182886b1edc42623987cac2095a0d407a5e334f37acdfa2f5` Source locator `/tasks/hard/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [ARC-AGI-1](https://benchize.com/benchmarks/arc-prize%3Av1_Semi_Private.md) | 91.17% | — | 56 / 213 | 0.34usd per task | — | [arc prize · v1](https://arcprize.org/media/data/leaderboard/v1.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.9116666666666666 \| score_fraction \| v1_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.33563630999999994 \| usd_per_task \| v1_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v1_Semi_Private harness Not reported modelGroup gemini-3-6-flash modelType CoT Reasoning effort high sourceModelVersion gemini-3-6-flash-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v1.json) Source arc prize Original model label Gemini 3.6 Flash (High) Source version v1 Observed 2026-10-21T16:34:20.378Z Evidence SHA-256 `302d8267c0522bf450ec1deeac4d060e2cf2fb444ba0a4269014d9535de0bd1f` Source locator `/evaluations/204` |  |  |  |  |  |  |  |
| [TaxEval v2 / stepwise reasoning](https://benchize.com/benchmarks/vals-ai%3Atax_eval_v2%3Astepwise_reasoning.md) | 86.18% | SE ±0.99 pp | 13 / 40 | $0.02 | 12.34source 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` \| 86.182 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.020385 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.335 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±0.99 pp sourcePopulation 145 stderr 0.987 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_eval_v2.B3yoffr8.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 2 Observed 2026-10-21T16:45:59.000Z Evidence SHA-256 `8b354a6ae848f5bb25a2e8b061b5f576d5b9e0c11b941dc1e6bed078e6529cd6` Source locator `/tasks/stepwise_reasoning/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [ARC-AGI-2](https://benchize.com/benchmarks/arc-prize%3Av2_Semi_Private.md) | 60.42% | — | 70 / 212 | 0.61usd per task | — | [arc prize · v2](https://arcprize.org/media/data/leaderboard/v2.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `score` \| 0.6041666666666666 \| score_fraction \| v2_Semi_Private \| Higher is better \| \| `cost_per_task` \| 0.6060796625000002 \| usd_per_task \| v2_Semi_Private \| Lower is better \| ### Configuration evaluationSplit v2_Semi_Private harness Not reported modelGroup gemini-3-6-flash modelType CoT Reasoning effort high sourceModelVersion gemini-3-6-flash-high thinkingEnabled true ### Source [Original source](https://arcprize.org/media/data/leaderboard/v2.json) Source arc prize Original model label Gemini 3.6 Flash (High) Source version v2 Observed 2026-10-21T16:34:20.750Z Evidence SHA-256 `bca68e12cc9a01954ae21b641844c1ecbabe146cb24b87f0f8e9b1db27433c29` Source locator `/evaluations/206` |  |  |  |  |  |  |  |
| [Tax Agent Bench / fact pattern analysis](https://benchize.com/benchmarks/vals-ai%3Atax_agent_bench%3Afact_pattern_analysis.md) | 16.28% | SE ±5.7 pp | 34 / 46 | $0.34 | 110.88source 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` \| 16.279 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.342251 \| USD \| per_test \| Lower is better \| \| `latency` \| 110.876 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.7 pp sourcePopulation 73 stderr 5.696 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_tax_agent_bench.BFpexnpS.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:55.958Z Evidence SHA-256 `446db182b67efb7923b3187a4040ec3a3ea492b8ad699a2b6d708d714cc063ac` Source locator `/tasks/fact_pattern_analysis/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text / industry writing and literature and language](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_writing_and_literature_and_language.md) | 1,469.61 | — | 22 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1469.6066284903093 \| rating \| reported \| Higher is better \| ### Configuration category industry_writing_and_literature_and_language config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1462.5598871917696 rank 23 upper 1476.653369788849 variance 12.92648580821495 votes 9845 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/7140/row` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate arbitration international dispute resolution](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__arbitration_international_dispute_resolution.md) | 78.85% | SE ±2.45 pp | 32 / 49 | $1.67 | 854.15source 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` \| 78.853 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.667616 \| USD \| per_test \| Lower is better \| \| `latency` \| 854.154 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.45 pp sourcePopulation 81 stderr 2.449 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__arbitration_international_dispute_resolution/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Terminal-Bench-Science / overall](https://benchize.com/benchmarks/vals-ai%3Aterminal-bench-science%3Aoverall.md) | 4.29% | SE ±2.44 pp | 18 / 30 | $4.39 | 6,744.66source duration | [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` \| 4.286 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.390771 \| USD \| per_test \| Lower is better \| \| `latency` \| 6744.655 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Mini-SWE-agent maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.44 pp sourcePopulation 41 stderr 2.438 tokenTotals {"cache_read_tokens":839068957,"cache_write_tokens":0,"input_tokens":1746051827,"output_tokens":13760141,"reasoning_tokens":3143772} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_terminal_bench_science.o-HR8Nyt.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 0.1 Observed 2026-10-21T16:46:03.529Z Evidence SHA-256 `a30a8618deaecf018ea1c8c9f675576cdd9ab79742d05788067db49afcc5f91b` Source locator `/tasks/overall/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [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) | 79.3% | SE ±2.19 pp | 34 / 49 | $2.12 | 1,010.13source 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` \| 79.3 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.121529 \| USD \| per_test \| Lower is better \| \| `latency` \| 1010.134 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.19 pp sourcePopulation 81 stderr 2.191 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__real_estate/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [IOI / overall](https://benchize.com/benchmarks/vals-ai%3Aioi%3Aoverall.md) | 35.06% | SE ±5.7 pp | 26 / 29 | $8.67 | 2,903.31source duration | [Vals AI · 2](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.056 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.66611 \| USD \| per_test \| Lower is better \| \| `latency` \| 2903.307 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.7 pp sourcePopulation 44 stderr 5.695 tokenTotals {"cache_read_tokens":232068785,"cache_write_tokens":0,"input_tokens":238444814,"output_tokens":1016307,"reasoning_tokens":489296} ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_ioi.CuUolFNv.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 2 Observed 2026-10-21T16:46:11.757Z Evidence SHA-256 `e1545b21b5b5c98d037aefa9d441b65859d07a10550f242d0e16162a49b8e8ab` Source locator `/tasks/overall/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / criteria pass rate bankruptcy restructuring](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acriteria_pass_rate__bankruptcy_restructuring.md) | 80.28% | SE ±2.35 pp | 26 / 49 | $2.79 | 1,149.7source 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` \| 80.277 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.792828 \| USD \| per_test \| Lower is better \| \| `latency` \| 1149.696 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.35 pp sourcePopulation 81 stderr 2.345 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/criteria_pass_rate__bankruptcy_restructuring/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Legal Research Bench / health](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Ahealth.md) | 36.67% | SE ±8.95 pp | 36 / 50 | $0.42 | 134.69source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 36.667 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.416767 \| USD \| per_test \| Lower is better \| \| `latency` \| 134.685 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.95 pp sourcePopulation 82 stderr 8.949 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/health/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Legal Research Bench / weighted pass civil litigation](https://benchize.com/benchmarks/vals-ai%3Alegal_research%3Aweighted_pass__civil_litigation.md) | 85.33% | SE ±2.94 pp | 29 / 50 | $0.48 | 192.42source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 85.331 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.477549 \| USD \| per_test \| Lower is better \| \| `latency` \| 192.418 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.94 pp sourcePopulation 82 stderr 2.941 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_legal_research.DiuL0R8P.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:52.389Z Evidence SHA-256 `26c58dfd47d0d2dc86f33c6d056f30309e0ee63570e7cd752c593b385f9d862e` Source locator `/tasks/weighted_pass__civil_litigation/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text style control / hard prompts english](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Ahard_prompts_english.md) | 1,499.72 | — | 29 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1499.7240115883055 \| rating \| reported \| Higher is better \| ### Configuration category hard_prompts_english config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1492.9067287285325 rank 33 upper 1506.5412944480786 variance 12.098358399624162 votes 10120 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/3900/row` |  |  |  |  |  |  |  |
| [APEX-Agents](https://benchize.com/benchmarks/mercor%3Aapex-agents%3A1.1.md) | 46.9% | — | 25 / 38 | — | — | [mercor · 1.1](https://www.mercor.com/apex/apex-agents-leaderboard/) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `pass_1` \| 46.9 \| percent \| task_completion_pass_at_1 \| Higher is better \| \| `mean_score` \| 63.4 \| 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 high ### Reported statistics reportedErrors {"mean_score":4.4,"pass_1":5.2} sampleSize 956 ### Source [Original source](https://www.mercor.com/apex/apex-agents-leaderboard/) Source mercor Original model label Gemini 3.6 Flash Source version 1.1 Observed 2026-10-21T16:33:27.509Z Evidence SHA-256 `359c569c3b0b62ab375895eabf3c45846fa45551d419d5c9d6a4c9117db78184` Source locator `/__NEXT_DATA__/props/pageProps/leaderboardData/21` |  |  |  |  |  |  |  |
| [Arena text / longer query](https://benchize.com/benchmarks/lmarena%3Atext%3Alonger_query.md) | 1,474.59 | — | 28 / 150 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1474.5897481675925 \| rating \| reported \| Higher is better \| ### Configuration category longer_query config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1468.6938208768431 rank 38 upper 1480.485675458342 variance 9.049155604776882 votes 17142 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/8555/row` |  |  |  |  |  |  |  |
| [Arena text / industry life and physical and social science](https://benchize.com/benchmarks/lmarena%3Atext%3Aindustry_life_and_physical_and_social_science.md) | 1,488.73 | — | 21 / 151 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1488.7282794399912 \| rating \| reported \| Higher is better \| ### Configuration category industry_life_and_physical_and_social_science config text Reasoning effort high thinkingEnabled true ### Reported statistics lower 1480.5161978538947 rank 25 upper 1496.9403610260879 variance 17.555383807165658 votes 5809 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `8e027ef69b8de06c4b2a8b217bfe816b1f1536269bb257fd295b4ef1ba8246ac` Source locator `/rows/5522/row` |  |  |  |  |  |  |  |
| [EMB / dataroom](https://benchize.com/benchmarks/vals-ai%3Aemb%3Adataroom.md) | 72.97% | SE ±9.18 pp | 34 / 47 | $2.58 | 569.26source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.965 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.583986 \| USD \| per_test \| Lower is better \| \| `latency` \| 569.256 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±9.18 pp sourcePopulation 76 stderr 9.182 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/dataroom/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena vision / creative writing vision (config: vision)](https://benchize.com/benchmarks/benchmark%3Avision%3Acreative_writing_vision--config-vision.md) | 1,278.38 | — | 29 / 70 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1278.3802439046713 \| rating \| reported \| Higher is better \| ### Configuration category creative_writing_vision config vision Reasoning effort high thinkingEnabled true ### Reported statistics lower 1256.3586336004828 rank 32 upper 1300.4018542088597 variance 126.24144707137815 votes 792 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/vision/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `06e61305486dce3fec5dc776ac2fd8321104e84c346cf9e08fa6f8e8a66ce0d7` Source locator `/rows/394/row` |  |  |  |  |  |  |  |
| [EMB / dcf](https://benchize.com/benchmarks/vals-ai%3Aemb%3Adcf.md) | 59.41% | SE ±6.35 pp | 16 / 47 | $3.07 | 686.71source duration | [Vals AI · 1](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.408 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.066222 \| USD \| per_test \| Lower is better \| \| `latency` \| 686.706 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.35 pp sourcePopulation 76 stderr 6.348 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/dcf/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Harvey's Legal Agent Benchmark v1 / corporate ma](https://benchize.com/benchmarks/vals-ai%3Ahlab-v1%3Acorporate_ma.md) | 0% | SE ±0 pp | 21 / 49 | $2.1 | 832.01source 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` \| 2.104291 \| USD \| per_test \| Lower is better \| \| `latency` \| 832.006 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Google reasoning Not reported Reasoning effort high Temperature 1 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 google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:45:53.909Z Evidence SHA-256 `65e7cd51e83066a42c9d782635dba5f2e9e1b189bd8118d3510cd17d2ddcba3f` Source locator `/tasks/corporate_ma/google~1gemini-3.6-flash` |  |  |  |  |  |  |  |
| [Arena text style control / math](https://benchize.com/benchmarks/lmarena%3Atext_style_control%3Amath.md) | 1,504.43 | — | 11 / 149 | — | — | [Arena](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `rating` \| 1504.4258593156294 \| rating \| reported \| Higher is better \| ### Configuration category math config text_style_control Reasoning effort high thinkingEnabled true ### Reported statistics lower 1490.3077668875098 rank 11 upper 1518.543951743749 variance 51.88667720064544 votes 1760 ### Source [Original source](https://datasets-server.huggingface.co/parquet/lmarena-ai%2Fleaderboard-dataset/text_style_control/latest) Source Arena Original model label Gemini 3.6 Flash (High) Observed 2026-10-21T18:45:05.190Z Evidence SHA-256 `d4875c03cb7ec0c6e8943c3145fd261225e8841b937240dc62a3032c4a798d84` Source locator `/rows/8923/row` |  |  |  |  |  |  |  |

[Next page](https://benchize.com/models/gemini-3-6-flash-high.md?cursor=5156f86695b0d0ae26c949a895f51d827c9d2e1d994c9b79483590d418ea540d)

---
Cite as: Gemini 3.6 FlashHigh — Benchize, https://benchize.com/models/gemini-3-6-flash-high (retrieved 2026-10-21)