# SAGE / PDEs > Source: Benchize (https://benchize.com) — https://benchize.com/benchmarks/vals-ai%3Asage%3APDEs. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/benchmarks/vals-ai%3Asage%3APDEs. Student Assessment with Generative Evaluation Canonical URL: https://benchize.com/benchmarks/vals-ai%3Asage%3APDEs 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 | [Gemma 4 31B](https://benchize.com/models/gemma-4-31b-it-high.md)High | 50.79% | SE ±6.27 pp | $0 | 106.92source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 50.794 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0 \| USD \| per_test \| Lower is better \| \| `latency` \| 106.921 \| 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: ±6.27 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 google/gemma-4-31b-it Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/PDEs/google~1gemma-4-31b-it` | | | | | | | | 2 | [Gemini 3.5 Flash-Lite](https://benchize.com/models/gemini-3-5-flash-lite-high.md)High | 49.21% | SE ±6.27 pp | $0.01 | 12.88source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 49.206 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.012636 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.879 \| 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: ±6.27 pp sourcePopulation 91 stderr 6.274 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/PDEs/google~1gemini-3.5-flash-lite` | | | | | | | | 3 | [DeepSeek V4.1 Flash](https://benchize.com/models/deepseek-v4-1-flash-high.md)High | 48.41% | SE ±6.27 pp | $0.01 | 43.48source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 48.413 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.014128 \| USD \| per_test \| Lower is better \| \| `latency` \| 43.479 \| 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: ±6.27 pp sourcePopulation 91 stderr 6.271 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/PDEs/deepseek~1deepseek-v4.1-flash` | | | | | | | | 4 | [Claude Opus 4.7](https://benchize.com/models/claude-opus-4-7-max.md)Max | 47.62% | SE ±6.27 pp | $0.35 | 131.16source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.619 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.353409 \| USD \| per_test \| Lower is better \| \| `latency` \| 131.155 \| 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: ±6.27 pp sourcePopulation 91 stderr 6.27 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/PDEs/anthropic~1claude-opus-4-7` | | | | | | | | 4 | [Gemini 3.1 Flash Lite Preview](https://benchize.com/models/gemini-3-1-flash-lite-preview-high.md)High | 47.62% | SE ±6.27 pp | $0.00931 | 18.89source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.619 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.009314 \| USD \| per_test \| Lower is better \| \| `latency` \| 18.889 \| 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: ±6.27 pp sourcePopulation 91 stderr 6.27 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/PDEs/google~1gemini-3.1-flash-lite-preview` | | | | | | | | 4 | [GPT-5.6 Sol](https://benchize.com/models/gpt-5-6-sol-max.md)Max | 47.62% | SE ±6.27 pp | $0.13 | 67.07source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.619 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.125985 \| USD \| per_test \| Lower is better \| \| `latency` \| 67.069 \| 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: ±6.27 pp sourcePopulation 91 stderr 6.27 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/PDEs/openai~1gpt-5.6-sol` | | | | | | | | 4 | [MiniMax M3](https://benchize.com/models/minimax-m3.md) | 47.62% | SE ±6.27 pp | $0.02 | 143.82source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 47.619 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.022988 \| USD \| per_test \| Lower is better \| \| `latency` \| 143.824 \| 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: ±6.27 pp sourcePopulation 91 stderr 6.27 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/PDEs/minimax~1MiniMax-M3` | | | | | | | | 8 | [Muse Spark 1.2](https://benchize.com/models/muse-spark-1-2-xhigh.md)Extra high | 44.44% | SE ±6.24 pp | $0.03 | 31.27source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.444 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.033761 \| USD \| per_test \| Lower is better \| \| `latency` \| 31.274 \| 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: ±6.24 pp sourcePopulation 91 stderr 6.24 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/PDEs/meta~1muse_spark_1_2` | | | | | | | | 8 | [Claude Opus 4.8](https://benchize.com/models/claude-opus-4-8-max.md)Max | 44.44% | SE ±6.24 pp | $0.49 | 203.74source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.444 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.494441 \| USD \| per_test \| Lower is better \| \| `latency` \| 203.742 \| 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: ±6.24 pp sourcePopulation 91 stderr 6.24 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/PDEs/anthropic~1claude-opus-4-8` | | | | | | | | 8 | [Claude Fable 5](https://benchize.com/models/claude-fable-5-max.md)Max | 44.44% | SE ±6.24 pp | $0.62 | 121.43source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 44.444 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.6238 \| USD \| per_test \| Lower is better \| \| `latency` \| 121.425 \| 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: ±6.24 pp sourcePopulation 91 stderr 6.24 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/PDEs/anthropic~1claude-fable-5` | | | | | | | | 11 | [Gemini 3.7 Flash](https://benchize.com/models/gemini-3-7-flash-high.md)High | 42.86% | SE ±6.22 pp | $0.02 | 8.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42.857 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.021721 \| USD \| per_test \| Lower is better \| \| `latency` \| 8.204 \| 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: ±6.22 pp sourcePopulation 91 stderr 6.216 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/PDEs/google~1gemini-3.7-flash` | | | | | | | | 11 | [Claude Sonnet 5](https://benchize.com/models/claude-sonnet-5-max.md)Max | 42.86% | SE ±6.22 pp | $0.57 | 430.47source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42.857 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.567587 \| USD \| per_test \| Lower is better \| \| `latency` \| 430.465 \| 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: ±6.22 pp sourcePopulation 91 stderr 6.216 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/PDEs/anthropic~1claude-sonnet-5` | | | | | | | | 11 | [Gemini 3.5 Flash](https://benchize.com/models/gemini-3-5-flash-high.md)High | 42.86% | SE ±6.22 pp | $0.06 | 47.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 42.857 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.057667 \| USD \| per_test \| Lower is better \| \| `latency` \| 47.196 \| 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: ±6.22 pp sourcePopulation 91 stderr 6.216 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/PDEs/google~1gemini-3.5-flash` | | | | | | | | 14 | [MiMo-V2.5](https://benchize.com/models/mimo-v2-5.md) | 41.27% | SE ±6.19 pp | $0.0039 | 64.98source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.27 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003898 \| USD \| per_test \| Lower is better \| \| `latency` \| 64.976 \| 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: ±6.19 pp sourcePopulation 91 stderr 6.185 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/PDEs/xiaomi~1mimo-v2.5` | | | | | | | | 14 | [Claude Sonnet 5.5](https://benchize.com/models/claude-sonnet-5-5-max.md)Max | 41.27% | SE ±6.19 pp | $0.2 | 124.55source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.27 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.195077 \| USD \| per_test \| Lower is better \| \| `latency` \| 124.552 \| 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: ±6.19 pp sourcePopulation 91 stderr 6.185 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/PDEs/anthropic~1claude-sonnet-5-5` | | | | | | | | 14 | [Claude Sonnet 4.6](https://benchize.com/models/claude-sonnet-4-6-max.md)Max | 41.27% | SE ±6.19 pp | $0.28 | 196.41source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.27 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.278746 \| USD \| per_test \| Lower is better \| \| `latency` \| 196.409 \| 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: ±6.19 pp sourcePopulation 91 stderr 6.185 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/PDEs/anthropic~1claude-sonnet-4-6` | | | | | | | | 14 | [Gemini 3 Flash Preview](https://benchize.com/models/gemini-3-flash-preview-high.md)High | 41.27% | SE ±6.18 pp | $0.02 | 47.13source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.27 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.020685 \| USD \| per_test \| Lower is better \| \| `latency` \| 47.126 \| 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: ±6.18 pp sourcePopulation 91 stderr 6.178 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/PDEs/google~1gemini-3-flash-preview` | | | | | | | | 14 | [Gemini 3.6 Flash](https://benchize.com/models/gemini-3-6-flash-high.md)High | 41.27% | SE ±6.19 pp | $0.05 | 24.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.27 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.050096 \| USD \| per_test \| Lower is better \| \| `latency` \| 24.974 \| 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: ±6.19 pp sourcePopulation 91 stderr 6.185 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/PDEs/google~1gemini-3.6-flash` | | | | | | | | 14 | [Mistral Medium 3.5](https://benchize.com/models/mistral-medium-3-5-high.md)High | 41.27% | SE ±6.19 pp | $0.08 | 66.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.27 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.079624 \| USD \| per_test \| Lower is better \| \| `latency` \| 66.2 \| 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: ±6.19 pp sourcePopulation 91 stderr 6.185 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/PDEs/mistralai~1mistral-medium-3.5` | | | | | | | | 14 | [Gemini 4 Argon](https://benchize.com/models/gemini-4-argon-high.md)High | 41.27% | SE ±6.19 pp | $0.09 | 61.7source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 41.27 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.094973 \| USD \| per_test \| Lower is better \| \| `latency` \| 61.704 \| 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: ±6.19 pp sourcePopulation 91 stderr 6.185 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/PDEs/google~1gemini-4-argon` | | | | | | | | 21 | [Gemini 3.1 Pro Preview](https://benchize.com/models/gemini-3-1-pro-preview-high.md)High | 39.68% | SE ±6.15 pp | $0.07 | 63.77source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.072766 \| USD \| per_test \| Lower is better \| \| `latency` \| 63.765 \| 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: ±6.15 pp sourcePopulation 91 stderr 6.148 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/PDEs/google~1gemini-3.1-pro-preview` | | | | | | | | 21 | [GPT-5.5](https://benchize.com/models/gpt-5-5-xhigh.md)Extra high | 39.68% | SE ±6.15 pp | $0.14 | 91.9source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.142524 \| USD \| per_test \| Lower is better \| \| `latency` \| 91.895 \| 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: ±6.15 pp sourcePopulation 91 stderr 6.148 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/PDEs/openai~1gpt-5.5` | | | | | | | | 21 | [MiMo-V2.6-Flash](https://benchize.com/models/mimo-v2-6-flash.md) | 39.68% | SE ±6.15 pp | $0.00388 | 144.75source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.003876 \| USD \| per_test \| Lower is better \| \| `latency` \| 144.753 \| 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: ±6.15 pp sourcePopulation 91 stderr 6.148 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/PDEs/xiaomi~1mimo-v2.6-flash` | | | | | | | | 21 | [Claude Haiku 5.5](https://benchize.com/models/claude-haiku-5-5-max.md)Max | 39.68% | SE ±6.15 pp | $0.02 | 143.97source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.019522 \| USD \| per_test \| Lower is better \| \| `latency` \| 143.966 \| 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: ±6.15 pp sourcePopulation 91 stderr 6.148 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/PDEs/anthropic~1claude-haiku-5-5` | | | | | | | | 21 | [Claude Opus 5](https://benchize.com/models/claude-opus-5-max.md)Max | 39.68% | SE ±6.15 pp | $0.16 | 54.4source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.161203 \| USD \| per_test \| Lower is better \| \| `latency` \| 54.396 \| 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: ±6.15 pp sourcePopulation 91 stderr 6.148 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/PDEs/anthropic~1claude-opus-5` | | | | | | | | 21 | [GPT-6 Astra](https://benchize.com/models/gpt-6-astra-max.md)Max | 39.68% | SE ±6.15 pp | $0.26 | 42.2source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.25889 \| USD \| per_test \| Lower is better \| \| `latency` \| 42.198 \| 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: ±6.15 pp sourcePopulation 91 stderr 6.148 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/PDEs/openai~1gpt-6-astra` | | | | | | | | 21 | [GPT-6.1 Sol](https://benchize.com/models/gpt-6-1-sol-max.md)Max | 39.68% | SE ±6.15 pp | $0.05 | 47.69source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.054022 \| USD \| per_test \| Lower is better \| \| `latency` \| 47.689 \| 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: ±6.15 pp sourcePopulation 91 stderr 6.148 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/PDEs/openai~1gpt-6.1-sol` | | | | | | | | 21 | [Muse Spark 1.1](https://benchize.com/models/muse-spark-1-1-xhigh.md)Extra high | 39.68% | SE ±6.15 pp | $0.03 | 52.87source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.025583 \| USD \| per_test \| Lower is better \| \| `latency` \| 52.873 \| 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: ±6.15 pp sourcePopulation 91 stderr 6.148 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/PDEs/meta~1muse_spark_1_1` | | | | | | | | 21 | [Claude Fable 5.1](https://benchize.com/models/claude-fable-5-1-max.md)Max | 39.68% | SE ±6.15 pp | $0.58 | 110.57source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 39.683 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.578727 \| USD \| per_test \| Lower is better \| \| `latency` \| 110.565 \| 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: ±6.15 pp sourcePopulation 91 stderr 6.148 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/PDEs/anthropic~1claude-fable-5-1` | | | | | | | | 30 | [GPT-5.6 Luna](https://benchize.com/models/gpt-5-6-luna-max.md)Max | 38.1% | SE ±6.1 pp | $0.01 | 52.28source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 38.095 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.010717 \| USD \| per_test \| Lower is better \| \| `latency` \| 52.28 \| 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: ±6.1 pp sourcePopulation 91 stderr 6.103 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/PDEs/openai~1gpt-5.6-luna` | | | | | | | | 30 | [GPT-6 Luna](https://benchize.com/models/gpt-6-luna-max.md)Max | 38.1% | SE ±6.1 pp | $0.00545 | 77.75source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 38.095 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.005451 \| USD \| per_test \| Lower is better \| \| `latency` \| 77.748 \| 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: ±6.1 pp sourcePopulation 91 stderr 6.103 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/PDEs/openai~1gpt-6-luna` | | | | | | | | 30 | [Claude Opus 5.5](https://benchize.com/models/claude-opus-5-5-max.md)Max | 38.1% | SE ±6.1 pp | $0.28 | 101.84source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 38.095 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.28379 \| USD \| per_test \| Lower is better \| \| `latency` \| 101.838 \| 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: ±6.1 pp sourcePopulation 91 stderr 6.103 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/PDEs/anthropic~1claude-opus-5-5` | | | | | | | | 30 | [GPT-5.6 Terra](https://benchize.com/models/gpt-5-6-terra-max.md)Max | 38.1% | SE ±6.1 pp | $0.04 | 44.22source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 38.095 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.042442 \| USD \| per_test \| Lower is better \| \| `latency` \| 44.223 \| 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: ±6.1 pp sourcePopulation 91 stderr 6.103 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/PDEs/openai~1gpt-5.6-terra` | | | | | | | | 30 | [MiMo-V2.6-Pro](https://benchize.com/models/mimo-v2-6-pro.md) | 38.1% | SE ±6.1 pp | $0.02 | 278.13source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 38.095 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.016908 \| USD \| per_test \| Lower is better \| \| `latency` \| 278.131 \| 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: ±6.1 pp sourcePopulation 91 stderr 6.103 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/PDEs/xiaomi~1mimo-v2.6-pro` | | | | | | | | 35 | [GPT-6 Sol](https://benchize.com/models/gpt-6-sol-max.md)Max | 36.51% | SE ±6.05 pp | $0.06 | 29.99source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 36.508 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.055244 \| USD \| per_test \| Lower is better \| \| `latency` \| 29.991 \| 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: ±6.05 pp sourcePopulation 91 stderr 6.052 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/PDEs/openai~1gpt-6-sol` | | | | | | | | 36 | [Gemini 2.5 Flash](https://benchize.com/models/gemini-2-5-flash.md) | 31.75% | SE ±5.84 pp | $0.00286 | 44.27source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 31.746 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00286 \| USD \| per_test \| Lower is better \| \| `latency` \| 44.271 \| 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: ±5.84 pp sourcePopulation 91 stderr 5.841 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/PDEs/google~1gemini-2.5-flash` | | | | | | | | 37 | [Gemini 2.5 Pro](https://benchize.com/models/gemini-2-5-pro.md) | 30.16% | SE ±5.76 pp | $0.00787 | 59.27source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30.159 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.00787 \| USD \| per_test \| Lower is better \| \| `latency` \| 59.266 \| 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: ±5.76 pp sourcePopulation 91 stderr 5.759 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/PDEs/google~1gemini-2.5-pro` | | | | | | | | 37 | [Gemini 3.8 Flash](https://benchize.com/models/gemini-3-8-flash-high.md)High | 30.16% | SE ±5.77 pp | $0.00662 | 25.76source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 30.159 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006618 \| USD \| per_test \| Lower is better \| \| `latency` \| 25.764 \| 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: ±5.77 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 google/gemini-3.8-flash Source version 1 Observed 2026-10-21T16:46:07.515Z Evidence SHA-256 `cc5fb3fecdb0382d492ff167a42ad84b9c5c3883373c78ed87baaa972b8b6f7c` Source locator `/tasks/PDEs/google~1gemini-3.8-flash` | | | | | | | | 39 | [Gemini 2.5 Flash Lite](https://benchize.com/models/gemini-2-5-flash-lite.md) | 20.64% | SE ±5.08 pp | $0.00112 | 12.78source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 20.635 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001121 \| USD \| per_test \| Lower is better \| \| `latency` \| 12.776 \| 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: ±5.08 pp sourcePopulation 91 stderr 5.078 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/PDEs/google~1gemini-2.5-flash-lite` | | | | | | | | 40 | [Mistral Large 3 2512](https://benchize.com/models/mistral-large-2512.md) | 17.46% | SE ±4.76 pp | $0.00627 | 53.01source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 17.46 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.006272 \| USD \| per_test \| Lower is better \| \| `latency` \| 53.013 \| 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: ±4.76 pp sourcePopulation 91 stderr 4.764 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/PDEs/mistralai~1mistral-large-2512` | | | | | | | | 41 | [Gemini 2.5 Flash Lite Preview 09-2025](https://benchize.com/models/gemini-2-5-flash-lite-preview-09-2025.md) | 13.49% | SE ±4.29 pp | $0.00127 | 11.27source duration | | | ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `accuracy` \| 13.492 \| percent \| reported \| Higher is better \| \| `cost_per_test` \| 0.001268 \| USD \| per_test \| Lower is better \| \| `latency` \| 11.273 \| 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: ±4.29 pp sourcePopulation 91 stderr 4.287 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/PDEs/google~1gemini-2.5-flash-lite-preview-09-2025` | | | | | | | --- Cite as: SAGE / PDEs — Benchize, https://benchize.com/benchmarks/vals-ai%3Asage%3APDEs (retrieved 2026-10-21)