GPQA Diamond
198 graduate-level science questions with 4 choices each (run by Epoch AI itself).
- Category
- Reasoning
- Unit
- Percent (%)
- Higher is better
- Comparison groups
- 1total
- Currently available model rankings · Ranked results: 8
- All models (records): Groups: 1 · Entries: 66
Rankings
Values with different source types (official, third-party, paper) or measurement conditions cannot be compared, so rankings are separated by comparison group (the same source, or sources verified to use the same conditions).
Rankings include only models currently available in Claude Code / Codex, excluding legacy models.
third-party results (Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0)
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | GPT-6 Astra | Max | 95.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-6-astra_max, Best score (across scorers)=0.9577020202020202, stderr=0.013696812097020311, Started at=2026-08-30T14:57:43.000Z |
| 2 | Claude Sonnet 5.5 | Max | 95.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-sonnet-5-5_max, Best score (across scorers)=0.9558080808080808, stderr=0.013710320714521202, Started at=2026-09-29T15:15:14.000Z |
| 3 | GPT-6.1 Sol | Max | 95.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6.1 Sol (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-6.1-sol_max, Best score (across scorers)=0.9539141414141414, stderr=0.013780748450364692, Started at=2026-09-29T22:00:34.000Z |
| 4 | GPT-6.1 Terra | Max | 94.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6.1 Terra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-6.1-terra_max, Best score (across scorers)=0.9431818181818182, stderr=0.014911672683567374, Started at=2026-10-26T20:00:37.000Z |
| 5 | Claude Fable 5.2 | Max | 93.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Fable 5.2 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-fable-5-2_max, Best score (across scorers)=0.9387626262626263, stderr=0.016253431037635206, Started at=2026-11-06T01:14:45.000Z |
| 6 | Claude Opus 5.5 | Max | 90.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-opus-5-5_max, Best score (across scorers)=0.9059343434343434, stderr=0.019434397190192135, Started at=2026-09-22T18:27:39.000Z |
| 7 | GPT-6 Luna | Max | 90.5% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-6-luna_max, Best score (across scorers)=0.9046717171717171, stderr=0.018537378631915503, Started at=2026-09-22T22:14:05.000Z |
| 8 | Claude Haiku 5.5 | Max | 89.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Haiku 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-haiku-5-5_max, Best score (across scorers)=0.8964646464646465, stderr=0.019774484382483127, Started at=2026-10-09T14:35:53.000Z |
All model rankings (records)
These rankings are recalculated by comparison group including legacy models and models unavailable in Claude Code / Codex. They differ from the rankings above because the set of models differs.
- View all model rankings (by metric)
- Cost balance (all models, records)
- Overall ranking (all models, records)
Show rankings including legacy and unavailable models (entries: 66)
third-party results (Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0)
| Rank | Model | effort | Score | Source cost (metric) | measured/reported by | source |
|---|---|---|---|---|---|---|
| 1 | Gemini 4 Carbon | High | 96.5% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 4 Carbon (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-4-carbon_high, Best score (across scorers)=0.9652777777777778, stderr=0.01207061012675132, Started at=2026-11-02T23:17:42.000Z |
| 2 | Gemini 4 Argon | High | 96.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 4 Argon (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-4-argon_high, Best score (across scorers)=0.9640151515151515, stderr=0.011918129589602694, Started at=2026-10-13T17:15:08.000Z |
| 3 | GPT-6 Astra | Max | 95.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Astra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-6-astra_max, Best score (across scorers)=0.9577020202020202, stderr=0.013696812097020311, Started at=2026-08-30T14:57:43.000Z |
| 4 | Claude Sonnet 5.5 | Max | 95.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-sonnet-5-5_max, Best score (across scorers)=0.9558080808080808, stderr=0.013710320714521202, Started at=2026-09-29T15:15:14.000Z |
| 5 | GPT-6.1 Sol | Max | 95.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6.1 Sol (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-6.1-sol_max, Best score (across scorers)=0.9539141414141414, stderr=0.013780748450364692, Started at=2026-09-29T22:00:34.000Z |
| 5 | Gemini 3.8 Flash | High | 95.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.8 Flash (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.8-flash_high, Best score (across scorers)=0.9539141414141414, stderr=0.01401136318210652, Started at=2026-09-02T17:15:36.000ZLocation gpqa_diamond.csv, data row 25 (file line 49), id=Br3mjs2GrYcCwX9AMwcihU, Model version=gemini-3.8-flash_high |
| 7 | Gemini 3.7 Flash | High | 94.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.7 Flash (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.7-flash_high, Best score (across scorers)=0.9482323232323232, stderr=0.013456525292246259, Started at=2026-08-14T18:29:12.000ZLocation gpqa_diamond.csv, data row 72 (file line 125), id=XyVL3VffJ6UboY97vxpohL, Model version=gemini-3.7-flash_high |
| 8 | Gemini 3.1 Pro Preview | High | 94.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.1-pro-preview_high, Best score (across scorers)=0.9444444444444444, stderr=0.016319950700767385, Started at=2026-08-06T22:30:37.000ZLocation gpqa_diamond.csv, data row 128 (file line 188), id=BgmrBFsbsaD8rNpebv49Da, Model version=gemini-3.1-pro-preview_high |
| 9 | GPT-6.1 Terra | Max | 94.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6.1 Terra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-6.1-terra_max, Best score (across scorers)=0.9431818181818182, stderr=0.014911672683567374, Started at=2026-10-26T20:00:37.000Z |
| 9 | GPT-6 Sol | Max | 94.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Sol (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-6-sol_max, Best score (across scorers)=0.9431818181818182, stderr=0.014938512008159717, Started at=2026-09-22T19:59:24.000ZLocation gpqa_diamond.csv, data row 22 (file line 46), id=aJD7ZfFftu2cZoToJhhzF7, Model version=gpt-6-sol_max |
| 11 | Kimi K3.1 Pro | Max | 94.2% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Kimi K3.1 Pro (Together, max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12. Epoch ran it via Together's inference API (Model version kimi-k3.1-pro-together).Source excerptgpqa_diamond.csv: Model version=kimi-k3.1-pro-together_max, Best score (across scorers)=0.9419191919191919, stderr=0.01439446786793499, Started at=2026-11-06T00:59:23.000ZLocation gpqa_diamond.csv, data row 2 (file line 3), id=2bhYPjF6VRWc5CeERGq8g5, Model version=kimi-k3.1-pro-together_max |
| 12 | Gemini 3.6 Flash | High | 94.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.6 Flash". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.6-flash_high, Best score (across scorers)=0.9412878787878788, stderr=0.014028967942064968, Started at=2026-08-02T00:21:27.000ZLocation gpqa_diamond.csv, data row 148 (file line 210), id=86SY5JbPB49xXhHFQW6tHu, Model version=gemini-3.6-flash_high |
| 13 | Gemini 3.1 Pro Preview | not stated | 94.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Pro Preview". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.Source excerptgpqa_diamond.csv: Model version=gemini-3.1-pro-preview, Best score (across scorers)=0.941, stderr=0.017, Started at=2026-02-20T05:01:02.541ZLocation gpqa_diamond.csv, data row 189 (file line 259), id=kR9F3oHBCnwQW4AiTPKwpd, Model version=gemini-3.1-pro-preview |
| 14 | Grok 4.6 | High | 94.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Grok 4.6 (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=grok-4.6_high, Best score (across scorers)=0.9400252525252525, stderr=0.014480018812911388, Started at=2026-08-12T19:39:52.000ZLocation gpqa_diamond.csv, data row 75 (file line 128), id=hnP6Z88x8bPEBRZ2PW6kps, Model version=grok-4.6_high |
| 15 | Claude Fable 5.2 | Max | 93.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Fable 5.2 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-fable-5-2_max, Best score (across scorers)=0.9387626262626263, stderr=0.016253431037635206, Started at=2026-11-06T01:14:45.000Z |
| 16 | GPT-5.6 Sol | Max | 93.5% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Sol (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.6-sol_max, Best score (across scorers)=0.9349747474747475, stderr=0.01570109070867593, Started at=2026-07-09T02:07:13.000ZLocation gpqa_diamond.csv, data row 170 (file line 240), id=nuKCgZReCBsXKCkNj9bK37, Model version=gpt-5.6-sol_max |
| 17 | GPT-5.6 Terra | Max | 93.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Terra (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.6-terra_max, Best score (across scorers)=0.9330808080808081, stderr=0.015363672147634115, Started at=2026-07-09T17:07:54.000ZLocation gpqa_diamond.csv, data row 168 (file line 238), id=4bLcFNu5zF6YuZf3qVKoHE, Model version=gpt-5.6-terra_max |
| 18 | Grok 4.6 | Xhigh | 93.2% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Grok 4.6 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=grok-4.6_xhigh, Best score (across scorers)=0.9318181818181818, stderr=0.015204299687218694, Started at=2026-08-14T13:47:42.000ZLocation gpqa_diamond.csv, data row 74 (file line 127), id=9YJf2nviwjM6WVhw8qeJta, Model version=grok-4.6_xhigh |
| 18 | DeepSeek-V4.1-Flash-1017 | Max | 93.2% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "DeepSeek V4.1 Flash 1017 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=deepseek-v4.1-flash-1017_max, Best score (across scorers)=0.9318181818181818, stderr=0.015671362011907143, Started at=2026-10-19T22:38:32.000ZLocation gpqa_diamond.csv, data row 12 (file line 24), id=ZK85PJtsCSeQJgV8dA4R4G, Model version=deepseek-v4.1-flash-1017_max |
| 20 | Kimi K3 | Max | 93.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Kimi K3 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=kimi-k3_max, Best score (across scorers)=0.9311868686868687, stderr=0.014937225364194858, Started at=2026-07-16T21:59:40.000ZLocation gpqa_diamond.csv, data row 153 (file lines 217-219; multi-line record), id=B8MaPUe3EYwUZASsNqE7C9, Model version=kimi-k3_max |
| 21 | Grok 4.7 | Xhigh | 92.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Grok 4.7 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=grok-4.7_xhigh, Best score (across scorers)=0.92739898989899, stderr=0.015505824295534454, Started at=2026-09-22T21:49:22.000ZLocation gpqa_diamond.csv, data row 21 (file line 45), id=hxAhYJfXdPNanxatXpG5hC, Model version=grok-4.7_xhigh |
| 22 | Qwen3.8-Max | Xhigh | 92.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Qwen3.8 Max (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=qwen3.8-max_xhigh, Best score (across scorers)=0.9267676767676768, stderr=0.01686498021450146, Started at=2026-08-04T16:28:46.000ZLocation gpqa_diamond.csv, data row 145 (file line 205), id=TEVNDC9QXBh7PQvX9kHZip, Model version=qwen3.8-max_xhigh |
| 23 | Kimi K3 | High | 91.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Kimi K3 (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=kimi-k3_high, Best score (across scorers)=0.9191919191919192, stderr=0.019417681889724515, Started at=2026-08-07T00:53:51.000ZLocation gpqa_diamond.csv, data row 86 (file lines 141-143; multi-line record), id=AoAD5uVtgVDnXmwA7STuno, Model version=kimi-k3_high |
| 24 | DeepSeek-V4-Pro-0813 | Max | 91.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "DeepSeek V4 Pro 0813 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=deepseek-v4-pro-0813_max, Best score (across scorers)=0.9166666666666666, stderr=0.015242573629934338, Started at=2026-08-18T21:03:23.000ZLocation gpqa_diamond.csv, data row 71 (file line 124), id=nEJGtXGN588zynPkynZkxz, Model version=deepseek-v4-pro-0813_max |
| 25 | GPT-5.6 Luna | Max | 91.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.6-luna_max, Best score (across scorers)=0.9160353535353535, stderr=0.01728284355494035, Started at=2026-07-09T13:36:49.000ZLocation gpqa_diamond.csv, data row 169 (file line 239), id=LWkDtkmd3TNmLzMhfZD5HW, Model version=gpt-5.6-luna_max |
| 26 | Claude Opus 4.8 | Max | 91.0% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.8". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-opus-4-8_max, Best score (across scorers)=0.9103535353535354, stderr=0.019157125794612026, Started at=2026-06-07T23:03:11.000ZLocation gpqa_diamond.csv, data row 176 (file line 246), id=dqgqP2uEPswfECCVj2Kbr9, Model version=claude-opus-4-8_max |
| 27 | GLM-5.3 | Max | 90.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GLM-5.3 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=glm-5.3_max, Best score (across scorers)=0.9090909090909091, stderr=0.015851578202142853, Started at=2026-08-24T19:44:18.000ZLocation gpqa_diamond.csv, data row 70 (file line 123), id=dLDBahYBTGRNjbsXA5pyr3, Model version=glm-5.3_max |
| 28 | GPT-5.5 | Low | 90.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.5_low, Best score (across scorers)=0.9065656565656566, stderr=0.017532658377721708, Started at=2026-05-05T18:00:18.624ZLocation gpqa_diamond.csv, data row 178 (file line 248), id=2CdomqtBVz2it7a2Zx2G2t, Model version=gpt-5.5_low |
| 29 | Claude Opus 5.5 | Max | 90.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-opus-5-5_max, Best score (across scorers)=0.9059343434343434, stderr=0.019434397190192135, Started at=2026-09-22T18:27:39.000Z |
| 30 | GPT-6 Luna | Max | 90.5% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-6 Luna (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-6-luna_max, Best score (across scorers)=0.9046717171717171, stderr=0.018537378631915503, Started at=2026-09-22T22:14:05.000Z |
| 31 | Claude Opus 4.7 | Xhigh | 90.2% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.7 (xhigh)". effort is indicated by the suffix _xhigh in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-opus-4-7_xhigh, Best score (across scorers)=0.9015151515151515, stderr=0.018464275887293338, Started at=2026-04-17T16:16:45.000ZLocation gpqa_diamond.csv, data row 182 (file line 252), id=VJezHrJ5YPCbpui8pZgcJg, Model version=claude-opus-4-7_xhigh |
| 31 | GLM-5.3-Flash | Max | 90.2% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GLM-5.3-Flash (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=glm-5.3-flash_max, Best score (across scorers)=0.9015151515151515, stderr=0.017183231147411448, Started at=2026-08-26T22:26:55.000ZLocation gpqa_diamond.csv, data row 69 (file lines 120-122; multi-line record), id=Jvt5BNr4ERbE9QGgMcEbmT, Model version=glm-5.3-flash_max |
| 33 | GPT-5.6 Sol | Low | 89.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Sol (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.6-sol_low, Best score (across scorers)=0.898989898989899, stderr=0.021469735576055356, Started at=2026-08-07T00:46:32.000ZLocation gpqa_diamond.csv, data row 90 (file line 147), id=6cmgkNAQZekBr6e6rVdLe9, Model version=gpt-5.6-sol_low |
| 34 | DeepSeek-V4.1-Flash | not stated | 89.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "DeepSeek V4.1 Flash (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12. No effort for the source effort label "max" because the official effort list has not been collected.Source excerptgpqa_diamond.csv: Model version=deepseek-v4.1-flash_max, Best score (across scorers)=0.8983585858585859, stderr=0.017287759372442393, Started at=2026-10-09T14:38:01.000ZLocation gpqa_diamond.csv, data row 16 (file lines 39-40; multi-line record), id=ZU5ebpDaDPiDZLgv7cG8B9, Model version=deepseek-v4.1-flash_max |
| 35 | Claude Haiku 5.5 | Max | 89.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Haiku 5.5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-haiku-5-5_max, Best score (across scorers)=0.8964646464646465, stderr=0.019774484382483127, Started at=2026-10-09T14:35:53.000Z |
| 36 | Gemini 3 Flash Preview | High | 89.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3 Flash Preview". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3-flash-preview_high, Best score (across scorers)=0.8939393939393939, stderr=0.021938047738853106, Started at=2026-08-06T22:22:58.000ZLocation gpqa_diamond.csv, data row 132 (file line 192), id=gVdraDT3pXmaExP9VbqME4, Model version=gemini-3-flash-preview_high |
| 37 | Claude Opus 4.6 | Max | 88.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.6 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-opus-4-6_max, Best score (across scorers)=0.8838383838383839, stderr=0.02282888177524936, Started at=2026-08-06T23:57:58.000ZLocation gpqa_diamond.csv, data row 121 (file line 179), id=JcQMgXdZKU54u52B8TGQKp, Model version=claude-opus-4-6_max |
| 37 | Claude Opus 4.8 | Low | 88.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.8". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-opus-4-8_low, Best score (across scorers)=0.8838383838383839, stderr=0.022828881775249357, Started at=2026-08-06T22:19:23.000ZLocation gpqa_diamond.csv, data row 138 (file line 198), id=GThtce6GAmRAS8srQyGQoA, Model version=claude-opus-4-8_low |
| 39 | Mistral Large 4 | High | 88.1% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Mistral Large 4 Preview (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12. Epoch's label is Mistral Large 4 Preview (2026-10-06 version; Mistral Large 4 from 2026-10-29 has a different Model version, mistral-large-4-0-oss, and is not included here).Source excerptgpqa_diamond.csv: Model version=mistral-large-4-0_high, Best score (across scorers)=0.8806818181818182, stderr=0.019328132475292338, Started at=2026-10-12T21:38:22.000ZLocation gpqa_diamond.csv, data row 15 (file lines 27-38; multi-line record), id=Ekx5phukyiJhAcQodMfS2p, Model version=mistral-large-4-0_high |
| 40 | GPT-5.6 Terra | Low | 87.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Terra (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.6-terra_low, Best score (across scorers)=0.8737373737373737, stderr=0.023664359402880177, Started at=2026-08-07T00:35:04.000ZLocation gpqa_diamond.csv, data row 96 (file line 154), id=JcuoAWhcnngPEZBPmiUyLF, Model version=gpt-5.6-terra_low |
| 41 | Gemini 3.6 Flash | Low | 86.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.6 Flash". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.6-flash_low, Best score (across scorers)=0.8636363636363636, stderr=0.02445015597318985, Started at=2026-08-06T22:36:03.000ZLocation gpqa_diamond.csv, data row 123 (file line 183), id=JoraLb9y55QXpMg4Rrmr5x, Model version=gemini-3.6-flash_low |
| 41 | Claude Opus 4.7 | Max | 86.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.7 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-opus-4-7_max, Best score (across scorers)=0.8636363636363636, stderr=0.02445015597318985, Started at=2026-08-06T22:19:01.000ZLocation gpqa_diamond.csv, data row 139 (file line 199), id=Ju7pUkkwYVj6ugi9Ri5Jjp, Model version=claude-opus-4-7_max |
| 43 | Gemini 3.6 Flash | Minimal | 85.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.6 Flash". effort is indicated by the suffix _minimal in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.6-flash_minimal, Best score (across scorers)=0.8585858585858586, stderr=0.024825909793343353, Started at=2026-08-07T00:17:01.000ZLocation gpqa_diamond.csv, data row 104 (file line 162), id=aPmR8fV49N98a6NVKpASAf, Model version=gemini-3.6-flash_minimal |
| 43 | Claude Fable 5 | Max | 85.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Fable 5 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-fable-5_max, Best score (across scorers)=0.8585858585858586, stderr=0.024825909793343353, Started at=2026-08-06T22:17:56.000ZLocation gpqa_diamond.csv, data row 140 (file line 200), id=S5pm7ctk9zgPfbyHrbD9AV, Model version=claude-fable-5_max |
| 45 | Claude Opus 4.8 | not stated | 85.4% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.8". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12. No effort because the source effort label "none" is not in the official effort list.Source excerptgpqa_diamond.csv: Model version=claude-opus-4-8_none, Best score (across scorers)=0.8535353535353535, stderr=0.025190921114603887, Started at=2026-08-06T22:19:27.000ZLocation gpqa_diamond.csv, data row 137 (file line 197), id=ckbZdkrXPwbFdjn6bmUQsi, Model version=claude-opus-4-8_none |
| 46 | Gemini 2.5 Pro | not stated | 85.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "gemini-2.5-pro". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.Source excerptgpqa_diamond.csv: Model version=gemini-2.5-pro, Best score (across scorers)=0.8529040404040404, stderr=0.02117010842348584, Started at=2025-11-16T19:00:08.124ZLocation gpqa_diamond.csv, data row 208 (file line 299), id=cqUZ6gcq2HBnShFRWvKjGr, Model version=gemini-2.5-pro |
| 47 | Kimi K3 | Low | 84.9% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Kimi K3 (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=kimi-k3_low, Best score (across scorers)=0.8484848484848485, stderr=0.025545650426603637, Started at=2026-08-07T00:54:16.000ZLocation gpqa_diamond.csv, data row 85 (file lines 138-140; multi-line record), id=mvNb3hNgSZ2gS6jHMtvCdk, Model version=kimi-k3_low |
| 48 | Gemini 3.5 Flash-Lite | High | 83.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.5 Flash-Lite". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.5-flash-lite_high, Best score (across scorers)=0.8333333333333334, stderr=0.026552207828215258, Started at=2026-08-06T22:35:04.000ZLocation gpqa_diamond.csv, data row 126 (file line 186), id=chbh6XstiqtUa5W9zuyfjS, Model version=gemini-3.5-flash-lite_high |
| 48 | Claude Fable 5 | High | 83.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Fable 5 (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-fable-5_high, Best score (across scorers)=0.8333333333333334, stderr=0.026552207828215258, Started at=2026-08-06T22:17:31.000ZLocation gpqa_diamond.csv, data row 142 (file line 202), id=d23hYvSNGFo7rniLFyBWiu, Model version=claude-fable-5_high |
| 48 | Claude Sonnet 4.6 | High | 83.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (high)". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-sonnet-4-6_high, Best score (across scorers)=0.8333333333333334, stderr=0.026552207828215258, Started at=2026-07-13T17:28:15.000ZLocation gpqa_diamond.csv, data row 162 (file line 232), id=DmdKPD9Z9RXwYyATAoG4Uw, Model version=claude-sonnet-4-6_high |
| 48 | Claude Sonnet 4.6 | Med | 83.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (medium)". effort is indicated by the suffix _medium in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-sonnet-4-6_medium, Best score (across scorers)=0.8333333333333334, stderr=0.026552207828215258, Started at=2026-07-13T17:28:00.000ZLocation gpqa_diamond.csv, data row 165 (file line 235), id=e8MXnAM8HMF8eEzYtYA7xv, Model version=claude-sonnet-4-6_medium |
| 52 | Gemini 3 Flash Preview | not stated | 83.2% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3 Flash Preview". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.Source excerptgpqa_diamond.csv: Model version=gemini-3-flash-preview, Best score (across scorers)=0.8320707070707071, stderr=0.019036353018587762, Started at=2025-12-17T22:39:00.278ZLocation gpqa_diamond.csv, data row 195 (file line 277), id=oAu9CZSNPZgwiwKnoNpM8Q, Model version=gemini-3-flash-preview |
| 53 | GPT-5.6 Sol | None | 82.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Sol (none)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.6-sol_none, Best score (across scorers)=0.8282828282828283, stderr=0.026869716187429872, Started at=2026-08-07T01:00:09.000ZLocation gpqa_diamond.csv, data row 83 (file line 136), id=DDfYPyKQW7vgDtGgkwcKSi, Model version=gpt-5.6-sol_none |
| 54 | GPT-5.6 Luna | Low | 82.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Luna (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.6-luna_low, Best score (across scorers)=0.8232323232323232, stderr=0.027178752639044908, Started at=2026-08-07T00:08:31.000ZLocation gpqa_diamond.csv, data row 108 (file line 166), id=nW39ZzuDQ3xTAGVoEfFG95, Model version=gpt-5.6-luna_low |
| 55 | Gemini 3.1 Flash-Lite | High | 81.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Flash-Lite". effort is indicated by the suffix _high in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.1-flash-lite_high, Best score (across scorers)=0.8181818181818182, stderr=0.027479603010538825, Started at=2026-08-06T22:26:07.000ZLocation gpqa_diamond.csv, data row 130 (file line 190), id=nE4hmJo3QV6X5jeGWAeAze, Model version=gemini-3.1-flash-lite_high |
| 56 | Claude Opus 4.5 | not stated | 80.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Opus 4.5 (no thinking)". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.Source excerptgpqa_diamond.csv: Model version=claude-opus-4-5-20251101, Best score (across scorers)=0.8068181818181818, stderr=0.023909479653766753, Started at=2025-11-24T19:57:20.151ZLocation gpqa_diamond.csv, data row 205 (file line 295), id=mEkZaYpiurQ6TEMAALK3su, Model version=claude-opus-4-5-20251101 |
| 57 | Claude Sonnet 4.6 | Max | 78.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.6 (max)". effort is indicated by the suffix _max in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-sonnet-4-6_max, Best score (across scorers)=0.7878787878787878, stderr=0.029126522834586777, Started at=2026-08-06T22:21:09.000ZLocation gpqa_diamond.csv, data row 134 (file line 194), id=SEePRKRcv8oqn5HpD2KFxB, Model version=claude-sonnet-4-6_max |
| 57 | Claude Fable 5 | Low | 78.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Fable 5 (low)". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=claude-fable-5_low, Best score (across scorers)=0.7878787878787878, stderr=0.029126522834586777, Started at=2026-08-06T22:17:37.000ZLocation gpqa_diamond.csv, data row 141 (file line 201), id=U5PsUdX2ak4kJ2hgnQkWnX, Model version=claude-fable-5_low |
| 59 | GPT-5.5 | None | 77.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.5 (no thinking)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.5_none, Best score (across scorers)=0.7727272727272727, stderr=0.029857515673386438, Started at=2026-08-07T00:57:11.000ZLocation gpqa_diamond.csv, data row 84 (file line 137), id=KesKa5EXtFG7H4UMBFzgCh, Model version=gpt-5.5_none |
| 59 | GPT-5.6 Terra | None | 77.3% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Terra (none)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.6-terra_none, Best score (across scorers)=0.7727272727272727, stderr=0.029857515673386438, Started at=2026-08-07T00:50:06.000ZLocation gpqa_diamond.csv, data row 87 (file line 144), id=F7v3JtKFb27j2YVmsndLM5, Model version=gpt-5.6-terra_none |
| 61 | Gemini 3.5 Flash-Lite | Low | 75.8% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.5 Flash-Lite". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.5-flash-lite_low, Best score (across scorers)=0.7575757575757576, stderr=0.030532892233932022, Started at=2026-08-06T22:35:12.000ZLocation gpqa_diamond.csv, data row 124 (file line 184), id=dgSJTFQ4UtuQKEhB9ss6K7, Model version=gemini-3.5-flash-lite_low |
| 62 | Gemini 3.5 Flash-Lite | Minimal | 74.2% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.5 Flash-Lite". effort is indicated by the suffix _minimal in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.5-flash-lite_minimal, Best score (across scorers)=0.7424242424242424, stderr=0.031156269519646826, Started at=2026-08-06T22:35:11.000ZLocation gpqa_diamond.csv, data row 125 (file line 185), id=7aAKcnsCXoSumfAu8mr2un, Model version=gemini-3.5-flash-lite_minimal |
| 62 | Gemini 3.1 Flash-Lite | Low | 74.2% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Flash-Lite". effort is indicated by the suffix _low in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.1-flash-lite_low, Best score (across scorers)=0.7424242424242424, stderr=0.03115626951964683, Started at=2026-08-06T22:25:58.000ZLocation gpqa_diamond.csv, data row 131 (file line 191), id=99ys2jgQiPQ5UwrqnazfqA, Model version=gemini-3.1-flash-lite_low |
| 64 | Gemini 3.1 Flash-Lite | Minimal | 73.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Gemini 3.1 Flash-Lite". effort is indicated by the suffix _minimal in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gemini-3.1-flash-lite_minimal, Best score (across scorers)=0.7373737373737373, stderr=0.031353050095330834, Started at=2026-08-06T22:26:14.000ZLocation gpqa_diamond.csv, data row 129 (file line 189), id=CmHy8cVECGkvQTwakfjRo2, Model version=gemini-3.1-flash-lite_minimal |
| 64 | Claude Sonnet 4.5 | not stated | 73.7% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "Claude Sonnet 4.5 (no thinking)". No effort suffix in Model version. Data retrieved 2026-11-12. No effort because effort is not stated in the source.Source excerptgpqa_diamond.csv: Model version=claude-sonnet-4-5-20250929, Best score (across scorers)=0.7373737373737373, stderr=0.031353050095330834, Started at=2025-09-29T18:04:57.033ZLocation gpqa_diamond.csv, data row 221 (file line 321), id=fsZmzw8jjyUgMQGwxodBwN, Model version=claude-sonnet-4-5-20250929 |
| 66 | GPT-5.6 Luna | None | 63.6% | — | Epoch AI | Epoch AI, Capabilities & benchmarking (benchmark_data.zip, gpqa_diamond.csv) CC BY 4.0Retrieved 2026-11-12 · Run by Epoch AI (third-party measurement). Source label "GPT-5.6 Luna (none)". effort is indicated by the suffix _none in Epoch's Model version. Data retrieved 2026-11-12.Source excerptgpqa_diamond.csv: Model version=gpt-5.6-luna_none, Best score (across scorers)=0.6363636363636364, stderr=0.03427308652999934, Started at=2026-08-07T00:35:08.000ZLocation gpqa_diamond.csv, data row 95 (file line 153), id=bDKKx7zTdW5WwMCfwqsLi4, Model version=gpt-5.6-luna_none |