# SAGE / overall > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Asage%3Aoverall. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Asage%3Aoverall. Student Assessment with Generative Evaluation Canonical URL: https://benchize.com/benchmarks/vals-ai%3Asage%3Aoverall 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 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 56.1% | SE ±3.37 pp | $0.33 | 124.65source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 56.103 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.330767 \| USD \| per_test \| Lower is better \| \| `latency` \| 124.647 \| 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: ±3.37 pp sourcePopulation 91 stderr 3.368 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/overall/anthropic~1claude-opus-4-7` | | | | | | | | 2 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it-high.md)High | 55.03% | SE ±3.41 pp | $0 | 93.06source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 55.034 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0 \| USD \| per_test \| Lower is better \| \| `latency` \| 93.058 \| 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: ±3.41 pp sourcePopulation 91 stderr 3.411 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/overall/google~1gemma-4-31b-it` | | | | | | | | 3 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 54.79% | SE ±3.35 pp | $0.51 | 185.59source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 54.788 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.5055 \| USD \| per_test \| Lower is better \| \| `latency` \| 185.594 \| 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: ±3.35 pp sourcePopulation 91 stderr 3.347 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/overall/anthropic~1claude-opus-4-8` | | | | | | | | 4 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 53.65% | SE ±3.39 pp | $0.1 | 63.07source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 53.645 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.097881 \| USD \| per_test \| Lower is better \| \| `latency` \| 63.068 \| 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: ±3.39 pp sourcePopulation 91 stderr 3.385 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/overall/google~1gemini-4-argon` | | | | | | | | 5 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 52.56% | SE ±3.42 pp | $0.15 | 75.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 52.563 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.147977 \| USD \| per_test \| Lower is better \| \| `latency` \| 75.395 \| 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: ±3.42 pp sourcePopulation 91 stderr 3.416 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/overall/openai~1gpt-5.6-sol` | | | | | | | | 6 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 51.89% | SE ±3.4 pp | $0.65 | 116.92source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.89 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.65214 \| USD \| per_test \| Lower is better \| \| `latency` \| 116.916 \| 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: ±3.4 pp sourcePopulation 91 stderr 3.4 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/overall/anthropic~1claude-fable-5` | | | | | | | | 7 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 51.85% | SE ±3.4 pp | $0.02 | 42.7source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.849 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.018229 \| USD \| per_test \| Lower is better \| \| `latency` \| 42.697 \| 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: ±3.4 pp sourcePopulation 91 stderr 3.404 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/overall/google~1gemini-3-flash-preview` | | | | | | | | 8 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 51.77% | SE ±3.41 pp | $0.18 | 113.42source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.772 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.178566 \| USD \| per_test \| Lower is better \| \| `latency` \| 113.423 \| 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: ±3.41 pp sourcePopulation 91 stderr 3.412 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/overall/anthropic~1claude-sonnet-5-5` | | | | | | | | 9 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 51.53% | SE ±3.95 pp | $0.14 | 76.05source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 51.532 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.136289 \| USD \| per_test \| Lower is better \| \| `latency` \| 76.05 \| 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: ±3.95 pp sourcePopulation 91 stderr 3.954 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/overall/openai~1gpt-5.5` | | | | | | | | 10 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 50.57% | SE ±3.44 pp | $0.03 | 118.54source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.574 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.025844 \| USD \| per_test \| Lower is better \| \| `latency` \| 118.538 \| 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: ±3.44 pp sourcePopulation 91 stderr 3.436 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/overall/minimax~1MiniMax-M3` | | | | | | | | 11 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 49.89% | SE ±3.44 pp | $0.05 | 32.59source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.885 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.052847 \| USD \| per_test \| Lower is better \| \| `latency` \| 32.592 \| 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: ±3.44 pp sourcePopulation 91 stderr 3.438 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/overall/google~1gemini-3.5-flash` | | | | | | | | 12 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 49.54% | SE ±3.48 pp | $0.00738 | 16.26source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.54 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.007378 \| USD \| per_test \| Lower is better \| \| `latency` \| 16.257 \| 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: ±3.48 pp sourcePopulation 91 stderr 3.484 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/overall/google~1gemini-3.1-flash-lite-preview` | | | | | | | | 13 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 49.43% | SE ±3.29 pp | $0.19 | 56.17source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.426 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.192726 \| USD \| per_test \| Lower is better \| \| `latency` \| 56.168 \| 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: ±3.29 pp sourcePopulation 91 stderr 3.291 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/overall/anthropic~1claude-opus-5` | | | | | | | | 14 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 49.23% | SE ±3.38 pp | $0.03 | 9.79source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.232 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.026336 \| USD \| per_test \| Lower is better \| \| `latency` \| 9.791 \| 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: ±3.38 pp sourcePopulation 91 stderr 3.382 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/overall/google~1gemini-3.7-flash` | | | | | | | | 15 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 48.93% | SE ±3.41 pp | $0.59 | 434.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.925 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.588528 \| USD \| per_test \| Lower is better \| \| `latency` \| 434.2 \| 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: ±3.41 pp sourcePopulation 91 stderr 3.405 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/overall/anthropic~1claude-sonnet-5` | | | | | | | | 16 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 48.69% | SE ±3.38 pp | $0.05 | 21.96source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.686 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.045301 \| USD \| per_test \| Lower is better \| \| `latency` \| 21.96 \| 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: ±3.38 pp sourcePopulation 91 stderr 3.383 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/overall/google~1gemini-3.6-flash` | | | | | | | | 17 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 48.68% | SE ±3.29 pp | $0.07 | 61.17source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.677 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.068908 \| USD \| per_test \| Lower is better \| \| `latency` \| 61.174 \| 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: ±3.29 pp sourcePopulation 91 stderr 3.293 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/overall/google~1gemini-3.1-pro-preview` | | | | | | | | 18 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 48.53% | SE ±3.34 pp | $0.61 | 105.75source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.526 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.61029 \| USD \| per_test \| Lower is better \| \| `latency` \| 105.745 \| 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: ±3.34 pp sourcePopulation 91 stderr 3.336 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/overall/anthropic~1claude-fable-5-1` | | | | | | | | 19 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 48.09% | SE ±3.38 pp | $0.00652 | 91.07source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.091 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006519 \| USD \| per_test \| Lower is better \| \| `latency` \| 91.072 \| 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: ±3.38 pp sourcePopulation 91 stderr 3.378 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/overall/openai~1gpt-6-luna` | | | | | | | | 20 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-high.md)High | 47.88% | SE ±3.44 pp | $0.01 | 35.78source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.88 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.01219 \| USD \| per_test \| Lower is better \| \| `latency` \| 35.776 \| 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: ±3.44 pp sourcePopulation 91 stderr 3.438 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/overall/deepseek~1deepseek-v4.1-flash` | | | | | | | | 21 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 47.66% | SE ±3.44 pp | $0.03 | 29.07source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.659 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.032261 \| USD \| per_test \| Lower is better \| \| `latency` \| 29.074 \| 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: ±3.44 pp sourcePopulation 91 stderr 3.44 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/overall/meta~1muse_spark_1_2` | | | | | | | | 22 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 47.3% | SE ±3.38 pp | $0.01 | 10.75source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.303 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010542 \| USD \| per_test \| Lower is better \| \| `latency` \| 10.751 \| 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: ±3.38 pp sourcePopulation 91 stderr 3.384 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/overall/google~1gemini-3.5-flash-lite` | | | | | | | | 23 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 47% | SE ±3.4 pp | $0.04 | 40.06source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.003 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.037793 \| USD \| per_test \| Lower is better \| \| `latency` \| 40.057 \| 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: ±3.4 pp sourcePopulation 91 stderr 3.403 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/overall/openai~1gpt-5.6-terra` | | | | | | | | 24 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max | 46.58% | SE ±3.43 pp | $0.23 | 163.37source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.582 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.234647 \| USD \| per_test \| Lower is better \| \| `latency` \| 163.365 \| 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: ±3.43 pp sourcePopulation 91 stderr 3.43 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/overall/anthropic~1claude-sonnet-4-6` | | | | | | | | 25 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 46.54% | SE ±3.46 pp | $0.06 | 50.22source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.538 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.061245 \| USD \| per_test \| Lower is better \| \| `latency` \| 50.219 \| 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: ±3.46 pp sourcePopulation 91 stderr 3.462 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/overall/openai~1gpt-6.1-sol` | | | | | | | | 26 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 46.37% | SE ±3.44 pp | $0.28 | 41.63source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 46.367 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.282823 \| USD \| per_test \| Lower is better \| \| `latency` \| 41.629 \| 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: ±3.44 pp sourcePopulation 91 stderr 3.444 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/overall/openai~1gpt-6-astra` | | | | | | | | 27 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 45.83% | SE ±3.36 pp | $0.33 | 114.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.831 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.332 \| USD \| per_test \| Lower is better \| \| `latency` \| 114.201 \| 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: ±3.36 pp sourcePopulation 91 stderr 3.36 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/overall/anthropic~1claude-opus-5-5` | | | | | | | | 28 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 45.78% | SE ±3.42 pp | $0.02 | 143.28source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.783 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.019327 \| USD \| per_test \| Lower is better \| \| `latency` \| 143.279 \| 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: ±3.42 pp sourcePopulation 91 stderr 3.423 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/overall/anthropic~1claude-haiku-5-5` | | | | | | | | 29 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 45.58% | SE ±3.28 pp | $0.03 | 49.95source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.58 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.025502 \| USD \| per_test \| Lower is better \| \| `latency` \| 49.948 \| 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: ±3.28 pp sourcePopulation 91 stderr 3.276 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/overall/meta~1muse_spark_1_1` | | | | | | | | 30 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 45.05% | SE ±3.4 pp | $0.02 | 219.91source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 45.05 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.017193 \| USD \| per_test \| Lower is better \| \| `latency` \| 219.909 \| 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: ±3.4 pp sourcePopulation 91 stderr 3.396 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/overall/xiaomi~1mimo-v2.6-pro` | | | | | | | | 31 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 44.79% | SE ±3.36 pp | $0.06 | 31.42source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.793 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.061332 \| USD \| per_test \| Lower is better \| \| `latency` \| 31.419 \| 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: ±3.36 pp sourcePopulation 91 stderr 3.364 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/overall/openai~1gpt-6-sol` | | | | | | | | 32 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 44.76% | SE ±3.42 pp | $0.00274 | 40.21source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.756 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.002737 \| USD \| per_test \| Lower is better \| \| `latency` \| 40.213 \| 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: ±3.42 pp sourcePopulation 91 stderr 3.418 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/overall/google~1gemini-2.5-flash` | | | | | | | | 33 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 44.22% | SE ±3.33 pp | $0.01 | 51.88source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.22 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010512 \| USD \| per_test \| Lower is better \| \| `latency` \| 51.878 \| 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: ±3.33 pp sourcePopulation 91 stderr 3.331 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/overall/openai~1gpt-5.6-luna` | | | | | | | | 34 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 43.53% | SE ±3.43 pp | $0.00492 | 136.14source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.53 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004922 \| USD \| per_test \| Lower is better \| \| `latency` \| 136.141 \| 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: ±3.43 pp sourcePopulation 91 stderr 3.429 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/overall/xiaomi~1mimo-v2.6-flash` | | | | | | | | 35 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 43.27% | SE ±3.39 pp | $0.0044 | 52.66source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 43.265 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.004398 \| USD \| per_test \| Lower is better \| \| `latency` \| 52.66 \| 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: ±3.39 pp sourcePopulation 91 stderr 3.387 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/overall/xiaomi~1mimo-v2.5` | | | | | | | | 36 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 41.92% | SE ±3.41 pp | $0.00881 | 52.93source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.916 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008806 \| USD \| per_test \| Lower is better \| \| `latency` \| 52.934 \| 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: ±3.41 pp sourcePopulation 91 stderr 3.411 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/overall/google~1gemini-2.5-pro` | | | | | | | | 37 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 37.61% | SE ±3.36 pp | $0.07 | 55.84source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 37.613 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.072775 \| USD \| per_test \| Lower is better \| \| `latency` \| 55.844 \| 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: ±3.36 pp sourcePopulation 91 stderr 3.356 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/overall/mistralai~1mistral-medium-3.5` | | | | | | | | 38 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 35.06% | SE ±3.36 pp | $0.00895 | 28.64source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 35.064 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.008954 \| USD \| per_test \| Lower is better \| \| `latency` \| 28.639 \| 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: ±3.36 pp sourcePopulation 91 stderr 3.364 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/overall/google~1gemini-3.8-flash` | | | | | | | | 39 | [Gemini 2.5 Flash Lite Preview 09-2025](https://benchize.com/models/gemini-2-5-flash-lite-preview-09-2025.md) | 27.97% | SE ±3.01 pp | $0.00113 | 14.67source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27.973 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001132 \| USD \| per_test \| Lower is better \| \| `latency` \| 14.674 \| 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: ±3.01 pp sourcePopulation 91 stderr 3.007 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/overall/google~1gemini-2.5-flash-lite-preview-09-2025` | | | | | | | | 40 | [Gemini 2.5 Flash Lite](https://benchize.com/models/gemini-2-5-flash-lite.md) | 27.53% | SE ±3.12 pp | $0.000929 | 13.78source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 27.533 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.000929 \| USD \| per_test \| Lower is better \| \| `latency` \| 13.781 \| 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: ±3.12 pp sourcePopulation 91 stderr 3.124 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/overall/google~1gemini-2.5-flash-lite` | | | | | | | | 41 | [Mistral Large 3 2512](https://benchize.com/models/mistral-large-2512.md) | 24.6% | SE ±2.81 pp | $0.00806 | 55.07source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 24.595 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00806 \| USD \| per_test \| Lower is better \| \| `latency` \| 55.068 \| 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: ±2.81 pp sourcePopulation 91 stderr 2.81 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/overall/mistralai~1mistral-large-2512` | | | | | | | --- Cite as: SAGE / overall — Benchize, https://benchize.com/benchmarks/vals-ai%3Asage%3Aoverall (retrieved 2026-10-21)