# EMB / misc > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc. Evaluating agents on Excel-based financial modeling tasks Canonical URL: https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc 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 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 73.95% | SE ±5.16 pp | $8.24 | 1,891.01source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 73.951 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.241005 \| USD \| per_test \| Lower is better \| \| `latency` \| 1891.012 \| 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: ±5.16 pp sourcePopulation 76 stderr 5.155 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/misc/google~1gemini-4-argon` | | | | | | | | 2 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 72.15% | SE ±3.88 pp | $11.68 | 1,464.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 72.15 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 11.677196 \| USD \| per_test \| Lower is better \| \| `latency` \| 1464.35 \| 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: ±3.88 pp sourcePopulation 76 stderr 3.878 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/misc/anthropic~1claude-fable-5-1` | | | | | | | | 3 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 71.4% | SE ±3.04 pp | $10.69 | 1,677.22source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 71.396 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.692038 \| USD \| per_test \| Lower is better \| \| `latency` \| 1677.222 \| 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: ±3.04 pp sourcePopulation 76 stderr 3.041 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/misc/anthropic~1claude-fable-5` | | | | | | | | 4 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 70.97% | SE ±3.18 pp | $9.16 | 1,828.93source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.972 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 9.159194 \| USD \| per_test \| Lower is better \| \| `latency` \| 1828.925 \| 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: ±3.18 pp sourcePopulation 76 stderr 3.179 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/misc/anthropic~1claude-opus-5-5` | | | | | | | | 5 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 70.94% | SE ±4.42 pp | $4.18 | 446.08source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.944 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.177008 \| USD \| per_test \| Lower is better \| \| `latency` \| 446.081 \| 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: ±4.42 pp sourcePopulation 76 stderr 4.419 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/misc/google~1gemini-3.7-flash` | | | | | | | | 6 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 70.41% | SE ±4.23 pp | $6.78 | 708.3source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.409 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.778419 \| USD \| per_test \| Lower is better \| \| `latency` \| 708.298 \| 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: ±4.23 pp sourcePopulation 76 stderr 4.23 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/misc/google~1gemini-3.8-flash` | | | | | | | | 7 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 70.14% | SE ±3.88 pp | $0.24 | 621.24source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 70.136 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.241467 \| USD \| per_test \| Lower is better \| \| `latency` \| 621.237 \| 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: ±3.88 pp sourcePopulation 76 stderr 3.88 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/misc/openai~1gpt-5.6-luna` | | | | | | | | 8 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 69.47% | SE ±4.19 pp | $2.49 | 675.14source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.468 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.493723 \| USD \| per_test \| Lower is better \| \| `latency` \| 675.136 \| 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 4.194 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/misc/openai~1gpt-5.6-terra` | | | | | | | | 9 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 69.08% | SE ±7.41 pp | $6.8 | 1,941.55source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 69.079 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.797643 \| USD \| per_test \| Lower is better \| \| `latency` \| 1941.547 \| 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: ±7.41 pp sourcePopulation 76 stderr 7.409 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/misc/anthropic~1claude-sonnet-5-5` | | | | | | | | 10 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 68.68% | SE ±3.13 pp | $3.28 | 545.11source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.681 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.282938 \| USD \| per_test \| Lower is better \| \| `latency` \| 545.114 \| 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: ±3.13 pp sourcePopulation 76 stderr 3.132 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/misc/openai~1gpt-5.6-sol` | | | | | | | | 11 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 68.59% | SE ±4.35 pp | $0.1 | 834.6source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 68.586 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.095388 \| USD \| per_test \| Lower is better \| \| `latency` \| 834.6 \| 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: ±4.35 pp sourcePopulation 76 stderr 4.353 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/misc/openai~1gpt-6-luna` | | | | | | | | 12 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 66.92% | SE ±3.23 pp | $4.77 | 1,491.38source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 66.921 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.772687 \| USD \| per_test \| Lower is better \| \| `latency` \| 1491.379 \| 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: ±3.23 pp sourcePopulation 76 stderr 3.233 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/misc/anthropic~1claude-opus-5` | | | | | | | | 13 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 64.97% | SE ±3.31 pp | $1.05 | 686.62source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.965 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.053988 \| USD \| per_test \| Lower is better \| \| `latency` \| 686.623 \| 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 3.308 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/misc/openai~1gpt-6-sol` | | | | | | | | 14 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 64.65% | SE ±6.9 pp | $2.91 | 985.39source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 64.647 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.912134 \| USD \| per_test \| Lower is better \| \| `latency` \| 985.394 \| 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: ±6.9 pp sourcePopulation 76 stderr 6.895 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/misc/openai~1gpt-5.5` | | | | | | | | 15 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 64.39% | SE ±3.01 pp | $2.63 | 583.67source duration | | | ### 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` | | | | | | | | 16 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 63.63% | SE ±6.65 pp | $0.09 | 2,091.33source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 63.627 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.093572 \| USD \| per_test \| Lower is better \| \| `latency` \| 2091.325 \| 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: ±6.65 pp sourcePopulation 76 stderr 6.653 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/misc/xiaomi~1mimo-v2.6-flash` | | | | | | | | 17 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 62.19% | SE ±6.98 pp | $4.5 | 1,022.57source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 62.192 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.497662 \| USD \| per_test \| Lower is better \| \| `latency` \| 1022.574 \| 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: ±6.98 pp sourcePopulation 76 stderr 6.979 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/misc/google~1gemini-3.5-flash` | | | | | | | | 18 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max | 61.69% | SE ±7.18 pp | $6.18 | 3,079.53source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.691 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 6.179184 \| USD \| per_test \| Lower is better \| \| `latency` \| 3079.529 \| 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: ±7.18 pp sourcePopulation 76 stderr 7.18 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/misc/anthropic~1claude-sonnet-4-6` | | | | | | | | 19 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 61.58% | SE ±6.2 pp | $0.7 | 903.52source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 61.58 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.704873 \| USD \| per_test \| Lower is better \| \| `latency` \| 903.517 \| 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: ±6.2 pp sourcePopulation 76 stderr 6.195 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/misc/openai~1gpt-6.1-sol` | | | | | | | | 20 | [DeepSeek V4.1 Flash 1017](https://benchize.com/models/deepseek-v4-1-flash-1017-max.md)Max | 60.9% | SE ±6.57 pp | $0.39 | 1,096.62source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 60.897 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.3924 \| USD \| per_test \| Lower is better \| \| `latency` \| 1096.615 \| 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: ±6.57 pp sourcePopulation 76 stderr 6.566 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/misc/deepseek~1deepseek-v4.1-flash-1017` | | | | | | | | 21 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 59.81% | SE ±6.13 pp | $3.82 | 594.87source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.814 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.821522 \| USD \| per_test \| Lower is better \| \| `latency` \| 594.866 \| 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: ±6.13 pp sourcePopulation 76 stderr 6.13 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/misc/openai~1gpt-6-astra` | | | | | | | | 22 | [Muse Spark 1.3](https://benchize.com/models/muse-spark-1-3-xhigh.md)Extra high | 59.55% | SE ±6.55 pp | $2.51 | 1,360.99source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.549 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.506718 \| USD \| per_test \| Lower is better \| \| `latency` \| 1360.993 \| 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: ±6.55 pp sourcePopulation 76 stderr 6.546 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/misc/meta~1muse_spark_1_3` | | | | | | | | 23 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 59.36% | SE ±8.87 pp | $13.12 | 2,930.21source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 59.355 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 13.123916 \| USD \| per_test \| Lower is better \| \| `latency` \| 2930.208 \| 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: ±8.87 pp sourcePopulation 76 stderr 8.87 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/misc/anthropic~1claude-opus-4-8` | | | | | | | | 24 | [DeepSeek V4 Pro](https://benchize.com/models/deepseek-v4-pro-max.md)Max | 57.65% | SE ±6.55 pp | $0.71 | 811.88source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.647 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.714205 \| USD \| per_test \| Lower is better \| \| `latency` \| 811.882 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.55 pp sourcePopulation 76 stderr 6.554 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/misc/deepseek~1deepseek-v4-pro` | | | | | | | | 25 | [DeepSeek V4 Flash 0731](https://benchize.com/models/deepseek-v4-flash-0731-high.md)High | 57.62% | SE ±6.14 pp | $0.44 | 2,071.46source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 57.615 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.439265 \| USD \| per_test \| Lower is better \| \| `latency` \| 2071.462 \| 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: ±6.14 pp sourcePopulation 76 stderr 6.136 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/misc/deepseek~1deepseek-v4-flash-0731` | | | | | | | | 26 | [Muse Wonder](https://benchize.com/models/muse-wonder-max.md)Max | 56.94% | SE ±8.78 pp | $3.12 | 951.46source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.936 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 3.120758 \| USD \| per_test \| Lower is better \| \| `latency` \| 951.464 \| 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: ±8.78 pp sourcePopulation 76 stderr 8.78 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/misc/meta~1muse-wonder` | | | | | | | | 27 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 54.31% | SE ±7.84 pp | $12.08 | 2,676.36source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.305 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 12.082044 \| USD \| per_test \| Lower is better \| \| `latency` \| 2676.363 \| 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: ±7.84 pp sourcePopulation 76 stderr 7.84 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/misc/anthropic~1claude-opus-4-7` | | | | | | | | 28 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 54.05% | SE ±6.46 pp | $0.07 | 1,667.86source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.045 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.069242 \| USD \| per_test \| Lower is better \| \| `latency` \| 1667.864 \| 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: ±6.46 pp sourcePopulation 76 stderr 6.46 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/misc/xiaomi~1mimo-v2.5` | | | | | | | | 29 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-high.md)High | 53.64% | SE ±7.97 pp | $0.24 | 833.5source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 53.636 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.238434 \| USD \| per_test \| Lower is better \| \| `latency` \| 833.498 \| 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: ±7.97 pp sourcePopulation 76 stderr 7.974 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/misc/deepseek~1deepseek-v4.1-flash` | | | | | | | | 30 | [DeepSeek V4 Pro 0813](https://benchize.com/models/deepseek-v4-pro-0813-max.md)Max | 52.79% | SE ±7.92 pp | $0.92 | 2,287.53source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.787 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.920573 \| USD \| per_test \| Lower is better \| \| `latency` \| 2287.526 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 384000 provider DeepSeek reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±7.92 pp sourcePopulation 76 stderr 7.917 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/misc/deepseek~1deepseek-v4-pro-0813` | | | | | | | | 31 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 52.26% | SE ±11.67 pp | $0.97 | 981.41source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.261 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.966232 \| USD \| per_test \| Lower is better \| \| `latency` \| 981.406 \| 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: ±11.67 pp sourcePopulation 76 stderr 11.667 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/misc/anthropic~1claude-haiku-5-5` | | | | | | | | 32 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 52.26% | SE ±9.6 pp | $8.26 | 2,692.47source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.26 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 8.259947 \| USD \| per_test \| Lower is better \| \| `latency` \| 2692.471 \| 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: ±9.6 pp sourcePopulation 76 stderr 9.595 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/misc/anthropic~1claude-sonnet-5` | | | | | | | | 33 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 50.69% | SE ±7.4 pp | $2.05 | 1,128.11source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.693 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.048008 \| USD \| per_test \| Lower is better \| \| `latency` \| 1128.107 \| 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: ±7.4 pp sourcePopulation 76 stderr 7.401 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/misc/meta~1muse_spark_1_2` | | | | | | | | 34 | [MiMo-V2.5-Pro](https://benchize.com/models/mimo-v2-5-pro.md) | 50.64% | SE ±6.18 pp | $0.18 | 1,867.77source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.644 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.178065 \| USD \| per_test \| Lower is better \| \| `latency` \| 1867.773 \| 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: ±6.18 pp sourcePopulation 76 stderr 6.183 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/misc/xiaomi~1mimo-v2.5-pro` | | | | | | | | 35 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 50.02% | SE ±5.09 pp | $2.18 | 2,177.18source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.022 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 2.184482 \| USD \| per_test \| Lower is better \| \| `latency` \| 2177.177 \| 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: ±5.09 pp sourcePopulation 76 stderr 5.091 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/misc/minimax~1MiniMax-M3` | | | | | | | | 36 | [Step 5 Preview](https://benchize.com/models/step-5-preview.md) | 49.45% | SE ±9.34 pp | $1.12 | 2,643.89source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.445 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.12199 \| USD \| per_test \| Lower is better \| \| `latency` \| 2643.893 \| 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: ±9.34 pp sourcePopulation 76 stderr 9.336 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/misc/stepfun~1step-5-preview` | | | | | | | | 37 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 48.82% | SE ±6.17 pp | $0.68 | 307.15source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.822 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.676879 \| USD \| per_test \| Lower is better \| \| `latency` \| 307.154 \| 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: ±6.17 pp sourcePopulation 76 stderr 6.172 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/misc/google~1gemini-3.5-flash-lite` | | | | | | | | 38 | [Muse Spark Open](https://benchize.com/models/muse-spark-open-xhigh.md)Extra high | 48.73% | SE ±6.96 pp | $4.42 | 5,020.41source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.727 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 4.421871 \| USD \| per_test \| Lower is better \| \| `latency` \| 5020.414 \| 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: ±6.96 pp sourcePopulation 76 stderr 6.961 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/misc/meta~1muse-spark-open` | | | | | | | | 39 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 48.03% | SE ±9.1 pp | $0.77 | 779.58source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.03 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.767546 \| USD \| per_test \| Lower is better \| \| `latency` \| 779.582 \| 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: ±9.1 pp sourcePopulation 76 stderr 9.095 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/misc/meta~1muse_spark_1_1` | | | | | | | | 40 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 43.37% | SE ±8.14 pp | $1.74 | 546.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.366 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.744042 \| USD \| per_test \| Lower is better \| \| `latency` \| 546.97 \| 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: ±8.14 pp sourcePopulation 76 stderr 8.142 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/misc/google~1gemini-3.1-pro-preview` | | | | | | | | 41 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 34.65% | SE ±10.58 pp | $0.25 | 4,606.65source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 34.646 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.246202 \| USD \| per_test \| Lower is better \| \| `latency` \| 4606.65 \| 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: ±10.58 pp sourcePopulation 76 stderr 10.58 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/misc/xiaomi~1mimo-v2.6-pro` | | | | | | | | 42 | [Nemotron 3 Ultra](https://benchize.com/models/nemotron-3-ultra-550b-a55b.md) | 33.6% | SE ±7.38 pp | — | 1,205.3source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.598 \| percent \| reported \| Higher is better \| \| `latency` \| 1205.295 \| 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: ±7.38 pp sourcePopulation 76 stderr 7.38 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/misc/nvidia~1nemotron-3-ultra-550b-a55b` | | | | | | | | 43 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 30.42% | SE ±7.94 pp | $0.38 | 257.18source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30.42 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.378937 \| USD \| per_test \| Lower is better \| \| `latency` \| 257.181 \| 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: ±7.94 pp sourcePopulation 76 stderr 7.939 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/misc/google~1gemini-3-flash-preview` | | | | | | | | 44 | [MiniMax M2.7](https://benchize.com/models/minimax-m2-7.md) | 28.95% | SE ±5.8 pp | $1.25 | 875.21source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 28.946 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 1.250699 \| USD \| per_test \| Lower is better \| \| `latency` \| 875.214 \| 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: ±5.8 pp sourcePopulation 76 stderr 5.797 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/misc/minimax~1MiniMax-M2.7` | | | | | | | | 45 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 14.1% | SE ±5.95 pp | $10.41 | 3,007.18source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 14.103 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 10.413594 \| USD \| per_test \| Lower is better \| \| `latency` \| 3007.183 \| 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: ±5.95 pp sourcePopulation 76 stderr 5.948 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/misc/mistralai~1mistral-medium-3.5` | | | | | | | | 46 | [Mercury 2.5](https://benchize.com/models/mercury-2-5-high.md)High | 12.54% | SE ±3.58 pp | $0.33 | 304.06source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 12.539 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.327239 \| USD \| per_test \| Lower is better \| \| `latency` \| 304.064 \| 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: ±3.58 pp sourcePopulation 76 stderr 3.581 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/misc/inception~1mercury-2.5` | | | | | | | | 47 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 8.7% | SE ±2.02 pp | $0.1 | 59.45source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 8.699 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.097216 \| USD \| per_test \| Lower is better \| \| `latency` \| 59.445 \| 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: ±2.02 pp sourcePopulation 76 stderr 2.021 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/misc/google~1gemini-3.1-flash-lite-preview` | | | | | | | --- Cite as: EMB / misc — Benchize, https://benchize.com/benchmarks/vals-ai%3Aemb%3Amisc (retrieved 2026-10-21)