# SAGE / automata > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Asage%3Aautomata. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Asage%3Aautomata. Student Assessment with Generative Evaluation Canonical URL: https://benchize.com/benchmarks/vals-ai%3Asage%3Aautomata 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. Student Assessment with Generative Evaluation Professional work · Models tested: 41 · Score publishers: Vals AI ## Model results | # | Model | Score | ± | Cost | Latency | | | --- | --- | --- | --- | --- | --- | --- | | 1 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 45.64% | SE ±6.39 pp | $0.11 | 76.41source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.635 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.10543 \| USD \| per_test \| Lower is better \| \| `latency` \| 76.406 \| 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: ±6.39 pp sourcePopulation 91 stderr 6.386 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-4-argon Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-4-argon` | | | | | | | | 2 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 44.05% | SE ±6.36 pp | $0.00268 | 47.36source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.048 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002682 \| USD \| per_test \| Lower is better \| \| `latency` \| 47.36 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.36 pp sourcePopulation 91 stderr 6.355 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-2.5-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-2.5-flash` | | | | | | | | 3 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 43.65% | SE ±6.33 pp | $0.00933 | 59.76source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.651 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009334 \| USD \| per_test \| Lower is better \| \| `latency` \| 59.764 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.33 pp sourcePopulation 91 stderr 6.33 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-2.5-pro Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-2.5-pro` | | | | | | | | 4 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 43.65% | SE ±6.32 pp | $0.33 | 145.36source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.65 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.329478 \| USD \| per_test \| Lower is better \| \| `latency` \| 145.362 \| 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: ±6.32 pp sourcePopulation 91 stderr 6.318 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-opus-4-7 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-opus-4-7` | | | | | | | | 5 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 43.25% | SE ±6.34 pp | $0.02 | 48.34source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.254 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.019315 \| USD \| per_test \| Lower is better \| \| `latency` \| 48.336 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.34 pp sourcePopulation 91 stderr 6.336 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3-flash-preview Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-3-flash-preview` | | | | | | | | 5 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 43.25% | SE ±6.28 pp | $0.22 | 139.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.254 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.219924 \| USD \| per_test \| Lower is better \| \| `latency` \| 139.345 \| 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: ±6.28 pp sourcePopulation 91 stderr 6.281 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-sonnet-5-5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-sonnet-5-5` | | | | | | | | 7 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 42.06% | SE ±6.26 pp | $0.0052 | 14.22source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42.064 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005199 \| USD \| per_test \| Lower is better \| \| `latency` \| 14.224 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.26 pp sourcePopulation 91 stderr 6.255 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3.1-flash-lite-preview Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-3.1-flash-lite-preview` | | | | | | | | 8 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it-high.md)High | 41.67% | SE ±6.32 pp | $0 | 77.76source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.666 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0 \| USD \| per_test \| Lower is better \| \| `latency` \| 77.76 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.32 pp sourcePopulation 91 stderr 6.317 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemma-4-31b-it Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemma-4-31b-it` | | | | | | | | 8 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 41.67% | SE ±6.31 pp | $0.61 | 236.05source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.666 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.61324 \| USD \| per_test \| Lower is better \| \| `latency` \| 236.054 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.31 pp sourcePopulation 91 stderr 6.311 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-opus-4-8 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-opus-4-8` | | | | | | | | 10 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 40.48% | SE ±8.87 pp | $0.15 | 91.56source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.476 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.151694 \| USD \| per_test \| Lower is better \| \| `latency` \| 91.557 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±8.87 pp sourcePopulation 91 stderr 8.871 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-5.5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/openai~1gpt-5.5` | | | | | | | | 10 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 40.48% | SE ±6.27 pp | $0.05 | 66.58source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 40.476 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.046792 \| USD \| per_test \| Lower is better \| \| `latency` \| 66.582 \| 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: ±6.27 pp sourcePopulation 91 stderr 6.273 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-6.1-sol Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/openai~1gpt-6.1-sol` | | | | | | | | 12 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 39.68% | SE ±6.18 pp | $0.78 | 152.56source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.682 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.779331 \| USD \| per_test \| Lower is better \| \| `latency` \| 152.558 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.18 pp sourcePopulation 91 stderr 6.183 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-fable-5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-fable-5` | | | | | | | | 12 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 39.68% | SE ±6.26 pp | $0.21 | 115.52source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.682 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.205378 \| USD \| per_test \| Lower is better \| \| `latency` \| 115.524 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.26 pp sourcePopulation 91 stderr 6.262 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-5.6-sol Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/openai~1gpt-5.6-sol` | | | | | | | | 14 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 38.89% | SE ±6.17 pp | $0.04 | 50.62source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 38.889 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.037181 \| USD \| per_test \| Lower is better \| \| `latency` \| 50.623 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.17 pp sourcePopulation 91 stderr 6.166 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-5.6-terra Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/openai~1gpt-5.6-terra` | | | | | | | | 15 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 38.49% | SE ±6.37 pp | $0.05 | 27.74source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 38.492 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.051282 \| USD \| per_test \| Lower is better \| \| `latency` \| 27.741 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.37 pp sourcePopulation 91 stderr 6.367 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3.5-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-3.5-flash` | | | | | | | | 16 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 37.7% | SE ±6.18 pp | $0.00761 | 135.1source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.698 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007607 \| USD \| per_test \| Lower is better \| \| `latency` \| 135.104 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.18 pp sourcePopulation 91 stderr 6.177 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-6-luna Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/openai~1gpt-6-luna` | | | | | | | | 17 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 37.3% | SE ±6.22 pp | $0.02 | 115.09source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.302 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.020054 \| USD \| per_test \| Lower is better \| \| `latency` \| 115.085 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider MiniMax reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.22 pp sourcePopulation 91 stderr 6.222 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label minimax/MiniMax-M3 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/minimax~1MiniMax-M3` | | | | | | | | 17 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 37.3% | SE ±6.23 pp | $0.24 | 53.38source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.302 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.23608 \| USD \| per_test \| Lower is better \| \| `latency` \| 53.38 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.23 pp sourcePopulation 91 stderr 6.228 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-6-astra Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/openai~1gpt-6-astra` | | | | | | | | 19 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 35.32% | SE ±6.14 pp | $0.03 | 12.05source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.318 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.028498 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.052 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.14 pp sourcePopulation 91 stderr 6.137 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3.7-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-3.7-flash` | | | | | | | | 19 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max | 35.32% | SE ±6.14 pp | $0.2 | 170.58source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.318 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.199244 \| USD \| per_test \| Lower is better \| \| `latency` \| 170.579 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning true Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.14 pp sourcePopulation 91 stderr 6.137 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-sonnet-4-6 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-sonnet-4-6` | | | | | | | | 19 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 35.32% | SE ±6.14 pp | $0.03 | 34.92source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.318 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.033644 \| USD \| per_test \| Lower is better \| \| `latency` \| 34.916 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.14 pp sourcePopulation 91 stderr 6.137 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label meta/muse_spark_1_2 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/meta~1muse_spark_1_2` | | | | | | | | 19 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 35.32% | SE ±6.13 pp | $0.02 | 182.43source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.318 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.023056 \| USD \| per_test \| Lower is better \| \| `latency` \| 182.426 \| 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: ±6.13 pp sourcePopulation 91 stderr 6.131 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-haiku-5-5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-haiku-5-5` | | | | | | | | 23 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 34.92% | SE ±6.06 pp | $0.00311 | 126.78source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 34.921 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003112 \| USD \| per_test \| Lower is better \| \| `latency` \| 126.784 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.06 pp sourcePopulation 91 stderr 6.061 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label xiaomi/mimo-v2.6-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/xiaomi~1mimo-v2.6-flash` | | | | | | | | 24 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 34.92% | SE ±6.2 pp | $0.8 | 677.5source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 34.92 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.801263 \| USD \| per_test \| Lower is better \| \| `latency` \| 677.504 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.2 pp sourcePopulation 91 stderr 6.195 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-sonnet-5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-sonnet-5` | | | | | | | | 24 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 34.92% | SE ±6.2 pp | $0.04 | 22.76source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 34.92 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.04337 \| USD \| per_test \| Lower is better \| \| `latency` \| 22.757 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.2 pp sourcePopulation 91 stderr 6.195 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3.6-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-3.6-flash` | | | | | | | | 26 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 34.52% | SE ±6 pp | $0.73 | 138.63source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 34.524 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.727769 \| USD \| per_test \| Lower is better \| \| `latency` \| 138.632 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6 pp sourcePopulation 91 stderr 6.002 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-fable-5-1 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-fable-5-1` | | | | | | | | 27 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 34.13% | SE ±6.06 pp | $0.01 | 207.75source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 34.127 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010334 \| USD \| per_test \| Lower is better \| \| `latency` \| 207.746 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.06 pp sourcePopulation 91 stderr 6.062 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label xiaomi/mimo-v2.6-pro Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/xiaomi~1mimo-v2.6-pro` | | | | | | | | 28 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 33.73% | SE ±5.99 pp | $0.05 | 45.35source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.73 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.049697 \| USD \| per_test \| Lower is better \| \| `latency` \| 45.352 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.99 pp sourcePopulation 91 stderr 5.985 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-6-sol Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/openai~1gpt-6-sol` | | | | | | | | 29 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 33.33% | SE ±6.17 pp | $0.00867 | 32.77source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.334 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008672 \| USD \| per_test \| Lower is better \| \| `latency` \| 32.772 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.17 pp sourcePopulation 91 stderr 6.173 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3.8-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-3.8-flash` | | | | | | | | 29 | [Gemini 2.5 Flash Lite](https://benchize.com/models/gemini-2-5-flash-lite.md) | 33.33% | SE ±6.02 pp | $0.000876 | 10.45source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 33.334 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.000876 \| USD \| per_test \| Lower is better \| \| `latency` \| 10.448 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.02 pp sourcePopulation 91 stderr 6.023 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-2.5-flash-lite Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-2.5-flash-lite` | | | | | | | | 31 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-high.md)High | 32.94% | SE ±6.1 pp | $0.00983 | 31.55source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 32.936 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00983 \| USD \| per_test \| Lower is better \| \| `latency` \| 31.551 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider DeepSeek reasoning Not reported Reasoning effort high Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±6.1 pp sourcePopulation 91 stderr 6.098 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label deepseek/deepseek-v4.1-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/deepseek~1deepseek-v4.1-flash` | | | | | | | | 32 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 32.54% | SE ±5.99 pp | $0.22 | 74.81source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 32.54 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.221359 \| USD \| per_test \| Lower is better \| \| `latency` \| 74.808 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.99 pp sourcePopulation 91 stderr 5.991 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-opus-5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-opus-5` | | | | | | | | 32 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 32.54% | SE ±5.99 pp | $0.42 | 150.94source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 32.54 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.418335 \| USD \| per_test \| Lower is better \| \| `latency` \| 150.936 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort max harness Not reported maxOutputTokens 30000 provider Anthropic reasoning Not reported Reasoning effort max Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.99 pp sourcePopulation 91 stderr 5.991 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label anthropic/claude-opus-5-5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/anthropic~1claude-opus-5-5` | | | | | | | | 34 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 32.14% | SE ±5.94 pp | $0.07 | 62.43source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 32.143 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.068462 \| USD \| per_test \| Lower is better \| \| `latency` \| 62.434 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.94 pp sourcePopulation 91 stderr 5.937 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3.1-pro-preview Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-3.1-pro-preview` | | | | | | | | 35 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 31.35% | SE ±5.77 pp | $0.01 | 70.07source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 31.35 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010871 \| USD \| per_test \| Lower is better \| \| `latency` \| 70.071 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider OpenAI reasoning Not reported Reasoning effort max Temperature Not reported topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.77 pp sourcePopulation 91 stderr 5.772 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label openai/gpt-5.6-luna Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/openai~1gpt-5.6-luna` | | | | | | | | 36 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 30.16% | SE ±5.7 pp | $0.07 | 54.58source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30.159 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.066288 \| USD \| per_test \| Lower is better \| \| `latency` \| 54.582 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Mistral AI reasoning Not reported Reasoning effort high Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.7 pp sourcePopulation 91 stderr 5.701 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label mistralai/mistral-medium-3.5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/mistralai~1mistral-medium-3.5` | | | | | | | | 37 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 29.76% | SE ±5.83 pp | $0.00244 | 50.8source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 29.762 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002438 \| USD \| per_test \| Lower is better \| \| `latency` \| 50.802 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Xiaomi reasoning Not reported Reasoning effort unknown Temperature 1 topP 0.95 verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.83 pp sourcePopulation 91 stderr 5.834 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label xiaomi/mimo-v2.5 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/xiaomi~1mimo-v2.5` | | | | | | | | 38 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 28.97% | SE ±5.86 pp | $0.00866 | 9.84source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 28.968 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008661 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.844 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort high Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.86 pp sourcePopulation 91 stderr 5.86 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-3.5-flash-lite Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-3.5-flash-lite` | | | | | | | | 39 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 28.17% | SE ±5.65 pp | $0.03 | 58.28source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 28.174 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.026942 \| USD \| per_test \| Lower is better \| \| `latency` \| 58.277 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Meta reasoning Not reported Reasoning effort xhigh Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.65 pp sourcePopulation 91 stderr 5.654 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label meta/muse_spark_1_1 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/meta~1muse_spark_1_1` | | | | | | | | 40 | [Gemini 2.5 Flash Lite Preview 09-2025](https://benchize.com/models/gemini-2-5-flash-lite-preview-09-2025.md) | 26.59% | SE ±5.65 pp | $0.00094 | 17.05source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 26.588 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00094 \| USD \| per_test \| Lower is better \| \| `latency` \| 17.054 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Google reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±5.65 pp sourcePopulation 91 stderr 5.653 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label google/gemini-2.5-flash-lite-preview-09-2025 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/google~1gemini-2.5-flash-lite-preview-09-2025` | | | | | | | | 41 | [Mistral Large 3 2512](https://benchize.com/models/mistral-large-2512.md) | 11.91% | SE ±4.15 pp | $0.00818 | 62.96source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 11.905 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00818 \| USD \| per_test \| Lower is better \| \| `latency` \| 62.961 \| source_duration \| reported_duration \| Lower is better \| ### Configuration computeEffort Not reported harness Not reported maxOutputTokens 30000 provider Mistral AI reasoning Not reported Reasoning effort unknown Temperature 1 topP Not reported verbosity Not reported ### Reported statistics Uncertainty Standard error: ±4.15 pp sourcePopulation 91 stderr 4.152 tokenTotals Not reported ### Source [Original source](https://www.vals.ai/_astro/benchmark_view_sage.RRwIIzO5.json) Source Vals AI Original model label mistralai/mistral-large-2512 Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/automata/mistralai~1mistral-large-2512` | | | | | | | --- Cite as: SAGE / automata — Benchize, https://benchize.com/benchmarks/vals-ai%3Asage%3Aautomata (retrieved 2026-10-21)