# EMB / template > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Aemb%3Atemplate. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Aemb%3Atemplate. Evaluating agents on Excel-based financial modeling tasks Canonical URL: https://benchize.com/benchmarks/vals-ai%3Aemb%3Atemplate 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. Evaluating agents on Excel-based financial modeling tasks Professional work · Models tested: 47 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 81.39% | SE ±2.55 pp | $10.77 | 1,928.47source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 81.385 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.771299 \| USD \| per_test \| Lower is better \| \| `latency` \| 1928.473 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.55 pp sourcePopulation 76 stderr 2.545 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-opus-5-5` | | | | | | | | 2 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 80.94% | SE ±2.62 pp | $9.01 | 2,158.23source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.939 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.010402 \| USD \| per_test \| Lower is better \| \| `latency` \| 2158.229 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.62 pp sourcePopulation 76 stderr 2.616 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-sonnet-5-5` | | | | | | | | 3 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 80.8% | SE ±2.54 pp | $16.56 | 1,699.44source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 80.796 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 16.559081 \| USD \| per_test \| Lower is better \| \| `latency` \| 1699.436 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.54 pp sourcePopulation 76 stderr 2.54 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-fable-5-1` | | | | | | | | 4 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 79.55% | SE ±2.89 pp | $16.14 | 2,452.6source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 79.553 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 16.142633 \| USD \| per_test \| Lower is better \| \| `latency` \| 2452.597 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 262144 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.89 pp sourcePopulation 76 stderr 2.887 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/google~1gemini-4-argon` | | | | | | | | 5 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 76.99% | SE ±2.63 pp | $12.64 | 1,549.9source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 76.991 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 12.636539 \| USD \| per_test \| Lower is better \| \| `latency` \| 1549.904 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.63 pp sourcePopulation 76 stderr 2.631 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-fable-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-fable-5` | | | | | | | | 6 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 75.58% | SE ±3.2 pp | $9.5 | 813.6source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.58 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.502756 \| USD \| per_test \| Lower is better \| \| `latency` \| 813.595 \| 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: ±3.2 pp sourcePopulation 76 stderr 3.201 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.8-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/google~1gemini-3.8-flash` | | | | | | | | 7 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 75.3% | SE ±3.07 pp | $7.9 | 558.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.303 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.895 \| USD \| per_test \| Lower is better \| \| `latency` \| 558.195 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.07 pp sourcePopulation 76 stderr 3.068 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.6-sol Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/openai~1gpt-5.6-sol` | | | | | | | | 8 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 75.07% | SE ±3.31 pp | $1 | 959.92source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 75.072 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.996387 \| USD \| per_test \| Lower is better \| \| `latency` \| 959.915 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.31 pp sourcePopulation 76 stderr 3.311 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6.1-sol Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/openai~1gpt-6.1-sol` | | | | | | | | 9 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 74.79% | SE ±3.34 pp | $5.77 | 721.49source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.785 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.767376 \| USD \| per_test \| Lower is better \| \| `latency` \| 721.493 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.34 pp sourcePopulation 76 stderr 3.343 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/openai~1gpt-6-astra` | | | | | | | | 10 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 74.69% | SE ±3.39 pp | $6.51 | 1,494.85source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 74.693 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.50608 \| USD \| per_test \| Lower is better \| \| `latency` \| 1494.85 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.39 pp sourcePopulation 76 stderr 3.393 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-opus-5` | | | | | | | | 11 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 73.6% | SE ±3.44 pp | $6.07 | 577.31source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.601 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.069648 \| USD \| per_test \| Lower is better \| \| `latency` \| 577.305 \| 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: ±3.44 pp sourcePopulation 76 stderr 3.437 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.7-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/google~1gemini-3.7-flash` | | | | | | | | 12 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 73.49% | SE ±3.38 pp | $1.33 | 555.71source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.488 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.329992 \| USD \| per_test \| Lower is better \| \| `latency` \| 555.706 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.38 pp sourcePopulation 76 stderr 3.378 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-sol Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/openai~1gpt-6-sol` | | | | | | | | 13 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 71.14% | SE ±3.7 pp | $12.96 | 2,724.16source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.143 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 12.960012 \| USD \| per_test \| Lower is better \| \| `latency` \| 2724.158 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.7 pp sourcePopulation 76 stderr 3.696 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-4-8 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-opus-4-8` | | | | | | | | 14 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 70.41% | SE ±3.7 pp | $0.17 | 1,085.67source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.405 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.174611 \| USD \| per_test \| Lower is better \| \| `latency` \| 1085.666 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.7 pp sourcePopulation 76 stderr 3.702 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/openai~1gpt-6-luna` | | | | | | | | 15 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 68.49% | SE ±4.05 pp | $2.26 | 672.66source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.49 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.258682 \| USD \| per_test \| Lower is better \| \| `latency` \| 672.659 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.05 pp sourcePopulation 76 stderr 4.047 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.6-terra Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/openai~1gpt-5.6-terra` | | | | | | | | 16 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 67.98% | SE ±4.19 pp | $10.12 | 2,843.86source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 67.983 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.117958 \| USD \| per_test \| Lower is better \| \| `latency` \| 2843.855 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.19 pp sourcePopulation 76 stderr 4.194 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-sonnet-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-sonnet-5` | | | | | | | | 17 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 65.73% | SE ±4.8 pp | $7.41 | 1,119.04source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 65.731 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.413135 \| USD \| per_test \| Lower is better \| \| `latency` \| 1119.036 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.8 pp sourcePopulation 76 stderr 4.795 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse-wonder Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/meta~1muse-wonder` | | | | | | | | 18 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 64.9% | SE ±4.55 pp | $0.37 | 3,392.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.902 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.368856 \| USD \| per_test \| Lower is better \| \| `latency` \| 3392.353 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.55 pp sourcePopulation 76 stderr 4.545 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label xiaomi/mimo-v2.6-pro Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/xiaomi~1mimo-v2.6-pro` | | | | | | | | 19 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 64.75% | SE ±4.19 pp | $0.49 | 634.71source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.747 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.491324 \| USD \| per_test \| Lower is better \| \| `latency` \| 634.713 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.19 pp sourcePopulation 76 stderr 4.193 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.6-luna Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/openai~1gpt-5.6-luna` | | | | | | | | 19 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 64.75% | SE ±3.84 pp | $4.25 | 698.33source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.747 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.247264 \| USD \| per_test \| Lower is better \| \| `latency` \| 698.325 \| 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 3.843 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/template/google~1gemini-3.6-flash` | | | | | | | | 21 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 64.56% | SE ±4.29 pp | $0.12 | 1,572.31source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.555 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.117057 \| USD \| per_test \| Lower is better \| \| `latency` \| 1572.313 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.29 pp sourcePopulation 76 stderr 4.288 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label xiaomi/mimo-v2.6-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/xiaomi~1mimo-v2.6-flash` | | | | | | | | 22 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 64.25% | SE ±5.35 pp | $1.12 | 1,031.12source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.253 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.118607 \| USD \| per_test \| Lower is better \| \| `latency` \| 1031.123 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.35 pp sourcePopulation 76 stderr 5.345 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-haiku-5-5` | | | | | | | | 23 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 62.53% | SE ±4.27 pp | $5.6 | 1,171.71source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.531 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 5.601891 \| USD \| per_test \| Lower is better \| \| `latency` \| 1171.71 \| 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: ±4.27 pp sourcePopulation 76 stderr 4.267 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.5-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/google~1gemini-3.5-flash` | | | | | | | | 24 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 61.81% | SE ±4.31 pp | $3.13 | 873.53source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.809 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.134312 \| USD \| per_test \| Lower is better \| \| `latency` \| 873.526 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.31 pp sourcePopulation 76 stderr 4.311 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/openai~1gpt-5.5` | | | | | | | | 25 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 60.42% | SE ±4.56 pp | $13.13 | 2,326.25source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.423 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.128173 \| USD \| per_test \| Lower is better \| \| `latency` \| 2326.254 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.56 pp sourcePopulation 76 stderr 4.558 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-opus-4-7 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-opus-4-7` | | | | | | | | 26 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-xhigh.md)Extra high | 59.21% | SE ±4.57 pp | $4.56 | 1,451.63source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.212 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.55582 \| USD \| per_test \| Lower is better \| \| `latency` \| 1451.63 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.57 pp sourcePopulation 76 stderr 4.569 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse_spark_1_3 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/meta~1muse_spark_1_3` | | | | | | | | 27 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max | 55.17% | SE ±4.81 pp | $6.85 | 3,118.88source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.17 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.851896 \| USD \| per_test \| Lower is better \| \| `latency` \| 3118.875 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 128000 provider Anthropic reasoning true Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.81 pp sourcePopulation 76 stderr 4.807 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/anthropic~1claude-sonnet-4-6` | | | | | | | | 28 | [DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max | 54.66% | SE ±5.19 pp | $0.36 | 1,003.78source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.659 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.362471 \| USD \| per_test \| Lower is better \| \| `latency` \| 1003.776 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.19 pp sourcePopulation 76 stderr 5.194 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash-1017 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/deepseek~1deepseek-v4.1-flash-1017` | | | | | | | | 29 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 52.24% | SE ±4.38 pp | $0.08 | 1,830.73source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.237 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.080822 \| USD \| per_test \| Lower is better \| \| `latency` \| 1830.734 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.38 pp sourcePopulation 76 stderr 4.375 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label xiaomi/mimo-v2.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/xiaomi~1mimo-v2.5` | | | | | | | | 30 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-high.md)High | 52.17% | SE ±4.6 pp | $0.41 | 1,608.94source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.167 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.410332 \| USD \| per_test \| Lower is better \| \| `latency` \| 1608.941 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.6 pp sourcePopulation 76 stderr 4.601 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4-flash-0731 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/deepseek~1deepseek-v4-flash-0731` | | | | | | | | 31 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 52.12% | SE ±4.68 pp | $0.23 | 1,742.23source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.116 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.231587 \| USD \| per_test \| Lower is better \| \| `latency` \| 1742.23 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.68 pp sourcePopulation 76 stderr 4.677 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label xiaomi/mimo-v2.5-pro Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/xiaomi~1mimo-v2.5-pro` | | | | | | | | 32 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 49.92% | SE ±4.96 pp | $2.88 | 1,084.28source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.917 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.878016 \| USD \| per_test \| Lower is better \| \| `latency` \| 1084.275 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.96 pp sourcePopulation 76 stderr 4.957 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse_spark_1_2 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/meta~1muse_spark_1_2` | | | | | | | | 33 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 49.41% | SE ±5.19 pp | $1.21 | 914.94source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.41 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.209257 \| USD \| per_test \| Lower is better \| \| `latency` \| 914.94 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 256000 provider Meta reasoning Not reported Reasoning effort xhigh Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.19 pp sourcePopulation 76 stderr 5.188 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse_spark_1_1 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/meta~1muse_spark_1_1` | | | | | | | | 34 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-high.md)High | 48.18% | SE ±5.24 pp | $0.26 | 846source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.181 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.257032 \| USD \| per_test \| Lower is better \| \| `latency` \| 845.999 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.24 pp sourcePopulation 76 stderr 5.238 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/deepseek~1deepseek-v4.1-flash` | | | | | | | | 35 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 47.42% | SE ±5.43 pp | $1.44 | 2,723.32source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.417 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.44076 \| USD \| per_test \| Lower is better \| \| `latency` \| 2723.319 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 1024000 provider Stepfun reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.43 pp sourcePopulation 76 stderr 5.427 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label stepfun/step-5-preview Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/stepfun~1step-5-preview` | | | | | | | | 36 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 47.21% | SE ±4.68 pp | $4.39 | 792.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.213 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.390484 \| USD \| per_test \| Lower is better \| \| `latency` \| 792.971 \| 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: ±4.68 pp sourcePopulation 76 stderr 4.677 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.1-pro-preview Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/google~1gemini-3.1-pro-preview` | | | | | | | | 37 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-max.md)Max | 46.07% | SE ±4.38 pp | $0.8 | 777.8source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.07 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.799253 \| USD \| per_test \| Lower is better \| \| `latency` \| 777.796 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.38 pp sourcePopulation 76 stderr 4.377 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4-pro Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/deepseek~1deepseek-v4-pro` | | | | | | | | 38 | [Muse Spark Open](https://benchize.com/models/muse-spark-open-xhigh.md)Extra high | 44.63% | SE ±4.97 pp | $7.01 | 5,739.05source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.632 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 7.009169 \| USD \| per_test \| Lower is better \| \| `latency` \| 5739.054 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 131072 provider Together AI reasoning Not reported Reasoning effort xhigh Temperature 1 topP 1 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.97 pp sourcePopulation 76 stderr 4.971 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label meta/muse-spark-open Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/meta~1muse-spark-open` | | | | | | | | 39 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 40.91% | SE ±4.56 pp | $1.31 | 509.54source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.906 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.314071 \| USD \| per_test \| Lower is better \| \| `latency` \| 509.542 \| 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: ±4.56 pp sourcePopulation 76 stderr 4.556 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.5-flash-lite Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/google~1gemini-3.5-flash-lite` | | | | | | | | 40 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 39.29% | SE ±5.18 pp | $1.12 | 2,234.02source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.291 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.117392 \| USD \| per_test \| Lower is better \| \| `latency` \| 2234.018 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.18 pp sourcePopulation 76 stderr 5.18 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label deepseek/deepseek-v4-pro-0813 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 41 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 34.55% | SE ±4.74 pp | $2.33 | 1,804.18source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 34.546 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.328648 \| USD \| per_test \| Lower is better \| \| `latency` \| 1804.175 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 512000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.74 pp sourcePopulation 76 stderr 4.741 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/minimax~1MiniMax-M3` | | | | | | | | 42 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 20.77% | SE ±4.22 pp | $0.5 | 355.34source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20.769 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.5034 \| USD \| per_test \| Lower is better \| \| `latency` \| 355.336 \| 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: ±4.22 pp sourcePopulation 76 stderr 4.223 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-flash-preview Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/google~1gemini-3-flash-preview` | | | | | | | | 43 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 19.8% | SE ±3.49 pp | $1.78 | 1,286.71source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 19.798 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.780973 \| USD \| per_test \| Lower is better \| \| `latency` \| 1286.708 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 80000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.49 pp sourcePopulation 76 stderr 3.487 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label minimax/MiniMax-M2.7 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/minimax~1MiniMax-M2.7` | | | | | | | | 44 | [Nemotron 3 Ultra](https://benchize.com/models/nemotron-3-ultra-550b-a55b.md) | 18.65% | SE ±3.83 pp | — | 1,984.68source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 18.647 \| percent \| reported \| Higher is better \| \| `latency` \| 1984.68 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 128000 provider Nvidia reasoning Not reported Reasoning effort unknown Temperature Not reported topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±3.83 pp sourcePopulation 76 stderr 3.826 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label nvidia/nemotron-3-ultra-550b-a55b Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/nvidia~1nemotron-3-ultra-550b-a55b` | | | | | | | | 45 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 8.14% | SE ±1.8 pp | $0.07 | 70.99source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 8.137 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.074608 \| USD \| per_test \| Lower is better \| \| `latency` \| 70.993 \| 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: ±1.8 pp sourcePopulation 76 stderr 1.799 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label google/gemini-3.1-flash-lite-preview Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/google~1gemini-3.1-flash-lite-preview` | | | | | | | | 46 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 7.39% | SE ±2.26 pp | $10.35 | 2,964.22source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 7.386 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.352195 \| USD \| per_test \| Lower is better \| \| `latency` \| 2964.222 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 80000 provider Mistral AI reasoning Not reported Reasoning effort high Temperature 0.7 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±2.26 pp sourcePopulation 76 stderr 2.262 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label mistralai/mistral-medium-3.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/mistralai~1mistral-medium-3.5` | | | | | | | | 47 | [Mercury 2.5](https://benchize.com/models/mercury-2-5-high.md)High | 4.83% | SE ±1.65 pp | $0.43 | 326.51source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 4.833 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.429915 \| USD \| per_test \| Lower is better \| \| `latency` \| 326.512 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 65536 provider Inception reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±1.65 pp sourcePopulation 76 stderr 1.652 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_emb.BY1LXsAw.json) Source Vals AI Original model label inception/mercury-2.5 Source version 1 Observed 2026-10-21T16:45:57.495Z Evidence SHA-256 `d807aee620ea47152a1fca0257a8dd12a1be4512c76cc1744c1ae9e285180918` Source locator `/tasks/template/inception~1mercury-2.5` | | | | | | | --- Cite as: EMB / template — Benchize, https://benchize.com/benchmarks/vals-ai%3Aemb%3Atemplate (retrieved 2026-10-21)