Benchmarks · reasoning
CritPt v2
CritPt v2: the authors' revision of CritPt's 70 research-level physics challenges, solved with a code-execution tool in an offline Python sandbox; accuracy.
Category
45 models · 93 results · data as of 2026-11-06 · artificialanalysis.ai ↗
Leaderboard
GPT-6 Astra medium
More from this benchmark
4 published measuresScore vs any published measure4 measures: sub-scores, splits, counts
27 more models under All models in settings.
Breakdown
darker is better within each column · click a column to sort| Model | ||||
|---|---|---|---|---|
| GPT-6 Astra medium | 1,142,499 | 197,640 | 167,522 | 795,996 |
| GPT-6.1 Sol max | 2,576,235 | 244,360 | 838,273 | 1,737,568 |
| Gemini 4 Carbon high | 92,232,418 | 1,716,018 | 5,465,333 | 84,159,671 |
| Opus 5.5 max | 35,698,555 | 613,881 | 4,443,628 | 30,618,722 |
| GPT-6.1 Terra max | 13,272,461 | 304,897 | 1,965,803 | 11,219,783 |
| GPT-6 Sol max | 9,882,745 | 226,892 | 1,311,781 | 8,508,308 |
| Fable 5.1 high | 10,125,511 | 378,189 | 1,512,055 | 8,201,499 |
| GPT-5.6 Sol max | 12,378,515 | 301,323 | 1,513,344 | 10,756,271 |
| Sonnet 5.5 max | 69,320,837 | 765,698 | 6,808,534 | 61,792,719 |
| Gemini 4 Argon high | 52,153,368 | 918,817 | 2,986,496 | 47,781,045 |
| Opus 5 max | 37,791,262 | 826,148 | 3,597,775 | 33,128,424 |
| Muse Wonder (Max) | 46,351,850 | 568,558 | 3,170,230 | 42,333,348 |
| Kimi K3.1 max | 26,437,373 | 385,656 | 2,430,946 | 23,546,844 |
| GPT-5.6 Terra max | 18,584,271 | 330,261 | 2,034,431 | 16,405,023 |
| Muse Spark 1.3 max | 58,166,511 | 982,147 | 3,999,604 | 53,027,490 |
| Haiku 5.5 xhigh | 32,524,438 | 542,641 | 4,403,413 | 27,772,163 |
| Gemini 3.8 Flash high | 102,251,086 | 1,321,639 | 2,948,282 | 97,580,855 |
| GPT-6 Luna max | 18,055,710 | 256,864 | 2,605,477 | 16,252,349 |
| Grok 4.6 xhigh | 42,682,926 | 639,949 | 2,751,515 | 39,384,023 |
| Grok 4.7 low | 44,607,223 | 693,605 | 2,090,883 | 41,426,082 |
| Kimi K3 max | 31,636,958 | 428,578 | 2,200,053 | 28,837,868 |
| Hy4 | 34,031,020 | 448,888 | 4,331,217 | 29,646,887 |
| GLM 5.3 max | 139,272,171 | 916,572 | 8,952,093 | 129,182,373 |
| MiMo V2.6 Pro | 86,649,636 | 725,647 | 6,060,033 | 79,479,748 |
| GPT-5.6 Luna max | 25,609,733 | 444,879 | 2,298,729 | 22,903,374 |
All results
93 rows| # | Model | Effort | CritPt v2 | Harness |
|---|---|---|---|---|
| 1 | GPT-6 Astra | medium | 84.0% | Stirrup |
| 2 | GPT-6 Astra | high | 83.7% | Stirrup |
| 3 | GPT-6 Astra | xhigh | 83.4% | Stirrup |
| 4 | GPT-6 Astra | max | 83.1% | Stirrup |
| 5 | GPT-6.1 Sol | max | 82.6% | Stirrup |
| 6 | GPT-6.1 Sol | xhigh | 82.6% | Stirrup |
| 7 | Gemini 4 Carbon | high | 82.3% | Stirrup |
| 8 | Gemini 4 Carbon | medium | 82.3% | Stirrup |
| 9 | GPT-6.1 Sol | high | 82.0% | Stirrup |
| 10 | Opus 5.5 | max | 81.7% | Stirrup |
| 11 | Opus 5.5 | xhigh | 81.4% | Stirrup |
| 12 | GPT-6.1 Terra | max | 81.4% | Stirrup |
| 13 | GPT-6 Sol | max | 80.9% | Stirrup |
| 14 | GPT-6.1 Sol | medium | 80.9% | Stirrup |
| 15 | Gemini 4 Carbon | low | 79.7% | Stirrup |
| 16 | GPT-6 Astra | low | 78.9% | Stirrup |
| 17 | GPT-6.1 Sol | low | 78.6% | Stirrup |
| 18 | Fable 5.1 | high | 77.7% | Stirrup |
| 19 | GPT-5.6 Sol | max | 77.1% | Stirrup |
| 20 | GPT-6.1 Terra | xhigh | 77.1% | Stirrup |
| 21 | GPT-6.1 Terra | high | 76.9% | Stirrup |
| 22 | Fable 5.1 | xhigh | 76.6% | Stirrup |
| 23 | Opus 5.5 | high | 76.0% | Stirrup |
| 24 | Sonnet 5.5 | max | 75.7% | Stirrup |
| 25 | Sonnet 5.5 | xhigh | 75.1% | Stirrup |
| 26 | GPT-6.1 Terra | medium | 74.6% | Stirrup |
| 27 | Fable 5.1 | medium | 73.4% | Stirrup |
| 28 | Fable 5.1 | max | 72.9% | Stirrup |
| 29 | Gemini 4 Argon | high | 72.9% | Stirrup |
| 30 | Opus 5.5 | medium | 72.3% | Stirrup |