CritPt
ReportedNo description yet: we only describe an eval set when we can do it correctly.
- Kind
- Published by a third party's leaderboard, collected by Epoch AI. The leaderboard is named and linked.
- Score shown
- Epoch's column "Accuracy", as a percentage, higher is better. The source gives no error bars.
- Results
- 271 in all: 105 for open-weight models, 166 for closed ones. 87 linked to a model page here.
Best open-weight result: mimo-v2.6-pro, 26.6%, number 44 of 271 results.
| # | Model | Weights | Setting | Score | Date | Source |
|---|---|---|---|---|---|---|
| 1 | gemini-4-carbon_highGoogle DeepMind | closed | effort high | 36.0% | not dated | via Epoch AI |
| 2 | claude-fable-5-2_xhighAnthropic | closed | effort xhigh | 35.7% | not dated | via Epoch AI |
| 3 | claude-fable-5-2_maxAnthropic | closed | effort max | 35.4% | not dated | via Epoch AI |
| 4 | claude-fable-5-2_highAnthropic | closed | effort high | 32.9% | not dated | via Epoch AI |
| 5 | gpt-5.6-sol_maxOpenAI | closed | effort max | 32.3% | not dated | via Epoch AI |
| 6 | claude-opus-5-5_maxAnthropic | closed | effort max | 31.7% | not dated | via Epoch AI |
| 7 | claude-opus-5-5_xhighAnthropic | closed | effort xhigh | 31.7% | not dated | via Epoch AI |
| 8 | gpt-6-astra_maxOpenAI | closed | effort max | 31.7% | not dated | via Epoch AI |
| 9 | gpt-6.1-sol_maxOpenAI | closed | effort max | 31.7% | not dated | via Epoch AI |
| 10 | gpt-6.1-sol_xhighOpenAI | closed | effort xhigh | 31.7% | not dated | via Epoch AI |
| 11 | claude-sonnet-5-5_maxAnthropic | closed | effort max | 31.4% | not dated | via Epoch AI |
| 12 | gpt-6-astra_xhighOpenAI | closed | effort xhigh | 31.4% | not dated | via Epoch AI |
| 13 | claude-fable-5-1_xhighAnthropic | closed | effort xhigh | 31.1% | not dated | via Epoch AI |
| 14 | claude-sonnet-5-5_xhighAnthropic | closed | effort xhigh | 31.1% | not dated | via Epoch AI |
| 15 | claude-fable-5-2_mediumAnthropic | closed | effort medium | 30.9% | not dated | via Epoch AI |
| 16 | claude-opus-5-5_highAnthropic | closed | effort high | 30.9% | not dated | via Epoch AI |
| 17 | gpt-6-sol_maxOpenAI | closed | effort max | 30.9% | not dated | via Epoch AI |
| 18 | gpt-5.5-pro_xhighOpenAI | closed | effort xhigh | 30.6% | not dated | via Epoch AI |
| 19 | claude-fable-5-1_highAnthropic | closed | effort high | 30.3% | not dated | via Epoch AI |
| 20 | gpt-5.4-pro-2026-03-05_xhighOpenAI | closed | effort xhigh | 30.0% | not dated | via Epoch AI |
| 21 | gpt-5.6-terra_maxOpenAI | closed | effort max | 30.0% | not dated | via Epoch AI |
| 22 | gpt-6.1-sol_highOpenAI | closed | effort high | 30.0% | not dated | via Epoch AI |
| 23 | claude-fable-5-1_maxAnthropic | closed | effort max | 29.7% | not dated | via Epoch AI |
| 24 | claude-fable-5-2_lowAnthropic | closed | effort low | 29.4% | not dated | via Epoch AI |
| 25 | claude-fable-5-1_mediumAnthropic | closed | effort medium | 29.1% | not dated | via Epoch AI |
| 26 | claude-opus-5_maxAnthropic | closed | effort max | 29.1% | not dated | via Epoch AI |
| 27 | gpt-6-astra_mediumOpenAI | closed | effort medium | 29.1% | not dated | via Epoch AI |
| 28 | gpt-6-astra_highOpenAI | closed | effort high | 28.9% | not dated | via Epoch AI |
| 29 | claude-fable-5_maxAnthropic | closed | effort max | 28.6% | not dated | via Epoch AI |
| 30 | gpt-5.6-sol_xhighOpenAI | closed | effort xhigh | 28.6% | not dated | via Epoch AI |
| 31 | claude-opus-5_highAnthropic | closed | effort high | 28.3% | not dated | via Epoch AI |
| 32 | muse-wonder-1.0_maxMeta AI | closed | effort max | 28.3% | not dated | via Epoch AI |
| 33 | gpt-6-sol_xhighOpenAI | closed | effort xhigh | 28.0% | not dated | via Epoch AI |
| 34 | gpt-6.1-terra_maxOpenAI | closed | effort max | 28.0% | not dated | via Epoch AI |
| 35 | claude-fable-5-1_lowAnthropic | closed | effort low | 27.7% | not dated | via Epoch AI |
| 36 | claude-opus-5_xhighAnthropic | closed | effort xhigh | 27.7% | not dated | via Epoch AI |
| 37 | claude-opus-5-5_mediumAnthropic | closed | effort medium | 27.7% | not dated | via Epoch AI |
| 38 | gpt-6.1-sol_mediumOpenAI | closed | effort medium | 27.7% | not dated | via Epoch AI |
| 39 | gemini-4-argon_highGoogle DeepMind | closed | effort high | 27.1% | not dated | via Epoch AI |
| 40 | gpt-5.5_xhighOpenAI | closed | effort xhigh | 27.1% | not dated | via Epoch AI |
| 41 | gpt-5.6-terra_xhighOpenAI | closed | effort xhigh | 27.1% | not dated | via Epoch AI |
| 42 | claude-opus-5_mediumAnthropic | closed | effort medium | 26.9% | not dated | via Epoch AI |
| 43 | gpt-6.1-terra_xhighOpenAI | closed | effort xhigh | 26.6% | not dated | via Epoch AI |
| 44 | mimo-v2.6-proXiaomi Corpno page match | open | default | 26.6% | not dated | via Epoch AI |
| 45 | gpt-6-astra_lowOpenAI | closed | effort low | 26.3% | not dated | via Epoch AI |
| 46 | muse-spark-1.3_xhighMeta AI | closed | effort xhigh | 26.0% | not dated | via Epoch AI |
| 47 | gemini-3-deep-think-previewGoogle DeepMind | closed | default | 25.7% | not dated | via Epoch AI |
| 48 | gpt-5.6-sol_highOpenAI | closed | effort high | 25.7% | not dated | via Epoch AI |
| 49 | gpt-6.1-terra_highOpenAI | closed | effort high | 25.7% | not dated | via Epoch AI |
| 50 | gpt-5.5_highOpenAI | closed | effort high | 25.4% | not dated | via Epoch AI |
| 51 | gpt-6-sol_highOpenAI | closed | effort high | 25.4% | not dated | via Epoch AI |
| 52 | gpt-6.1-sol_lowOpenAI | closed | effort low | 24.9% | not dated | via Epoch AI |
| 53 | muse-spark-1.3_maxMeta AI | closed | effort max | 24.9% | not dated | via Epoch AI |
| 54 | claude-sonnet-5-5_highAnthropic | closed | effort high | 24.6% | not dated | via Epoch AI |
| 55 | gpt-6-sol_mediumOpenAI | closed | effort medium | 24.6% | not dated | via Epoch AI |
| 56 | moonshotai/Kimi-K3.1-ProEpoch: kimi-k3.1-pro_unknown, Moonshot | open | effort unknown | 24.6% | not dated | via Epoch AI |
| 57 | deepseek-ai/DeepSeek-V4.1-Flash-1017Epoch: deepseek-v4.1-flash-1017_max, DeepSeek | open | effort max | 24.0% | not dated | via Epoch AI |
| 58 | gpt-5.4-2026-03-05_xhighOpenAI | closed | effort xhigh | 23.4% | not dated | via Epoch AI |
| 59 | moonshotai/Kimi-K3Epoch: kimi-k3_max, Moonshot | open | effort max | 23.4% | not dated | via Epoch AI |
| 60 | claude-opus-5_lowAnthropic | closed | effort low | 23.1% | not dated | via Epoch AI |
| 61 | gemini-4-argon_mediumGoogle DeepMind | closed | effort medium | 23.1% | not dated | via Epoch AI |
| 62 | gpt-5.6-sol_mediumOpenAI | closed | effort medium | 22.9% | not dated | via Epoch AI |
| 63 | gpt-5.6-terra_highOpenAI | closed | effort high | 22.9% | not dated | via Epoch AI |
| 64 | claude-haiku-5-5_xhighAnthropic | closed | effort xhigh | 22.6% | not dated | via Epoch AI |
| 65 | gpt-6.1-terra_mediumOpenAI | closed | effort medium | 21.4% | not dated | via Epoch AI |
| 66 | claude-opus-4-8_maxAnthropic | closed | effort max | 20.9% | not dated | via Epoch AI |
| 67 | zai-org/GLM-5.2Epoch: glm-5.2_max, Z.ai (Zhipu AI) | open | effort max | 20.9% | not dated | via Epoch AI |
| 68 | step-5-preview_unknownStepFun | closed | effort unknown | 20.9% | not dated | via Epoch AI |
| 69 | gpt-5.6-luna_maxOpenAI | closed | effort max | 20.6% | not dated | via Epoch AI |
| 70 | gpt-5.6-luna_xhighOpenAI | closed | effort xhigh | 20.6% | not dated | via Epoch AI |
| 71 | qwen3.8-max_unknownAlibaba | closed | effort unknown | 20.0% | not dated | via Epoch AI |
| 72 | gpt-6-astra_noneOpenAI | closed | effort none | 19.7% | not dated | via Epoch AI |
| 73 | grok-4.6_xhighxAI | closed | effort xhigh | 19.7% | not dated | via Epoch AI |
| 74 | gpt-6-luna_maxOpenAI | closed | effort max | 19.4% | not dated | via Epoch AI |
| 75 | zai-org/GLM-5.3Epoch: glm-5.3_max, Z.ai (Zhipu AI) | open | effort max | 19.1% | not dated | via Epoch AI |
| 76 | claude-haiku-5-5_maxAnthropic | closed | effort max | 18.9% | not dated | via Epoch AI |
| 77 | claude-haiku-5-5_highAnthropic | closed | effort high | 18.6% | not dated | via Epoch AI |
| 78 | deepseek-ai/DeepSeek-V4-Pro-0813Epoch: deepseek-v4-pro-0813_high, DeepSeek | open | effort high | 18.6% | not dated | via Epoch AI |
| 79 | gpt-5.5_mediumOpenAI | closed | effort medium | 18.6% | not dated | via Epoch AI |
| 80 | gemini-3.8-flash_highGoogle DeepMind | closed | effort high | 18.3% | not dated | via Epoch AI |
| 81 | deepseek-ai/DeepSeek-V4-Pro-0813Epoch: deepseek-v4-pro-0813_max, DeepSeek | open | effort max | 18.0% | not dated | via Epoch AI |
| 82 | grok-4.7_highxAI | closed | effort high | 18.0% | not dated | via Epoch AI |
| 83 | claude-opus-5-5_lowAnthropic | closed | effort low | 17.7% | not dated | via Epoch AI |
| 84 | gemini-3.1-pro-previewGoogle DeepMind | closed | default | 17.7% | not dated | via Epoch AI |
| 85 | grok-4.6_mediumxAI | closed | effort medium | 17.7% | not dated | via Epoch AI |
| 86 | grok-4.7_xhighxAI | closed | effort xhigh | 17.7% | not dated | via Epoch AI |
| 87 | muse-spark-1.2_xhighMeta AI | closed | effort xhigh | 17.7% | not dated | via Epoch AI |
| 88 | qwen3.8-max-0902_unknownAlibaba | closed | effort unknown | 17.7% | not dated | via Epoch AI |
| 89 | gpt-5.6-terra_mediumOpenAI | closed | effort medium | 17.4% | not dated | via Epoch AI |
| 90 | gpt-6-luna_xhighOpenAI | closed | effort xhigh | 17.4% | not dated | via Epoch AI |
| 91 | grok-4.6_highxAI | closed | effort high | 17.1% | not dated | via Epoch AI |
| 92 | claude-sonnet-5_maxAnthropic | closed | effort max | 16.9% | not dated | via Epoch AI |
| 93 | claude-sonnet-5-5_mediumAnthropic | closed | effort medium | 16.9% | not dated | via Epoch AI |
| 94 | gpt-5.3-codex_xhighOpenAI | closed | effort xhigh | 16.9% | not dated | via Epoch AI |
| 95 | deepseek-ai/DeepSeek-V4-Flash-0731Epoch: deepseek-v4-flash-0731_max, DeepSeek | open | effort max | 16.6% | not dated | via Epoch AI |
| 96 | gpt-5.6-luna_highOpenAI | closed | effort high | 16.6% | not dated | via Epoch AI |
| 97 | gpt-6-sol_lowOpenAI | closed | effort low | 16.3% | not dated | via Epoch AI |
| 98 | claude-sonnet-5_xhighAnthropic | closed | effort xhigh | 15.4% | not dated | via Epoch AI |
| 99 | zai-org/GLM-5.3-FlashEpoch: glm-5.3-flash_unknown, Z.ai (Zhipu AI) | open | effort unknown | 15.4% | not dated | via Epoch AI |
| 100 | gpt-6-luna_highOpenAI | closed | effort high | 15.4% | not dated | via Epoch AI |
| 101 | grok-4.5_highxAI | closed | effort high | 15.4% | not dated | via Epoch AI |
| 102 | gpt-6.1-terra_lowOpenAI | closed | effort low | 15.1% | not dated | via Epoch AI |
| 103 | muse-spark-1.1_xhighMeta AI | closed | effort xhigh | 15.1% | not dated | via Epoch AI |
| 104 | muse-spark-1.1Meta AI | closed | default | 15.1% | not dated | via Epoch AI |
| 105 | gpt-5.6-sol_lowOpenAI | closed | effort low | 14.9% | not dated | via Epoch AI |
| 106 | meta-models/Muse-Spark-Open-816B-A42BEpoch: Muse-Spark-Open-816B-A42B_xhigh, Meta AI | open | effort xhigh | 14.9% | not dated | via Epoch AI |
| 107 | zai-org/GLM-5.3Epoch: glm-5.3_low, Z.ai (Zhipu AI) | open | effort low | 14.6% | not dated | via Epoch AI |
| 108 | deepseek-ai/DeepSeek-V4.1-FlashEpoch: deepseek-v4.1-flash_max, DeepSeek | open | effort max | 14.3% | not dated | via Epoch AI |
| 109 | gemini-3.7-flash_highGoogle DeepMind | closed | effort high | 14.3% | not dated | via Epoch AI |
| 110 | grok-4.7_lowxAI | closed | effort low | 13.4% | not dated | via Epoch AI |
| 111 | qwen3.7-maxAlibaba | closed | default | 13.4% | not dated | via Epoch AI |
| 112 | beam-1.0_unknownReflectionno page match | open | effort unknown | 13.1% | not dated | via Epoch AI |
| 113 | gemini-3.5-flash_highGoogle DeepMind | closed | effort high | 13.1% | not dated | via Epoch AI |
| 114 | claude-haiku-5-5_mediumAnthropic | closed | effort medium | 12.9% | not dated | via Epoch AI |
| 115 | deepseek-ai/DeepSeek-V4-ProEpoch: deepseek-v4-pro_max, DeepSeek | open | effort max | 12.9% | not dated | via Epoch AI |
| 116 | gpt-5-2025-08-07_highOpenAI | closed | effort high | 12.6% | not dated | via Epoch AI |
| 117 | gemini-3.8-flash_mediumGoogle DeepMind | closed | effort medium | 12.3% | not dated | via Epoch AI |
| 118 | claude-opus-4-7_maxAnthropic | closed | effort max | 12.0% | not dated | via Epoch AI |
| 119 | mimo-v2.6-flashXiaomi Corpno page match | open | default | 12.0% | not dated | via Epoch AI |
| 120 | claude-sonnet-5-5_lowAnthropic | closed | effort low | 11.4% | not dated | via Epoch AI |
| 121 | muse-sparkMeta AI | closed | default | 11.3% | not dated | via Epoch AI |
| 122 | mistral-large-4-0-oss_mediumMistral AIno page match | open | effort medium | 11.1% | not dated | via Epoch AI |
| 123 | gemini-3.6-flash_highGoogle DeepMind | closed | effort high | 10.6% | not dated | via Epoch AI |
| 124 | gpt-6-luna_mediumOpenAI | closed | effort medium | 10.6% | not dated | via Epoch AI |
| 125 | mistral-large-4-0_unknownMistral AIno page match | open | effort unknown | 10.6% | not dated | via Epoch AI |
| 126 | deepseek-ai/DeepSeek-V4-ProEpoch: deepseek-v4-pro_high, DeepSeek | open | effort high | 10.0% | not dated | via Epoch AI |
| 127 | gpt-5.4-mini-2026-03-17_xhighOpenAI | closed | effort xhigh | 10.0% | not dated | via Epoch AI |
| 128 | moonshotai/Kimi-K2.7-CodeEpoch: kimi-k2.7-code, Moonshot | open | default | 10.0% | not dated | via Epoch AI |
| 129 | mistral-large-4-0-oss_highMistral AIno page match | open | effort high | 10.0% | not dated | via Epoch AI |
| 130 | gemini-3.7-flash_mediumGoogle DeepMind | closed | effort medium | 9.4% | not dated | via Epoch AI |
| 131 | gpt-5.6-terra_lowOpenAI | closed | effort low | 9.4% | not dated | via Epoch AI |
| 132 | gpt-5.4-nano-2026-03-17_xhighOpenAI | closed | effort xhigh | 9.3% | not dated | via Epoch AI |
| 133 | claude-haiku-5-5_lowAnthropic | closed | effort low | 9.1% | not dated | via Epoch AI |
| 134 | grok-build-0.1xAI | closed | default | 9.1% | not dated | via Epoch AI |
| 135 | qwen3.7-plusAlibaba | closed | default | 9.1% | not dated | via Epoch AI |
| 136 | claude-sonnet-5_mediumAnthropic | closed | effort medium | 8.6% | not dated | via Epoch AI |
| 137 | thinkingmachines/Inkling-SmallEpoch: inkling-small, Thinking Machines | open | default | 8.3% | not dated | via Epoch AI |
| 138 | gpt-5.5_lowOpenAI | closed | effort low | 8.0% | not dated | via Epoch AI |
| 139 | grok-4.3_highxAI | closed | effort high | 8.0% | not dated | via Epoch AI |
| 140 | moonshotai/Kimi-K2.6Epoch: kimi-k2.6, Moonshot | open | default | 8.0% | not dated | via Epoch AI |
| 141 | deepseek-ai/DeepSeek-V4-FlashEpoch: deepseek-v4-flash_max, DeepSeek | open | effort max | 7.1% | not dated | via Epoch AI |
| 142 | gemini-3-pro-previewGoogle DeepMind | closed | default | 6.9% | not dated | via Epoch AI |
| 143 | gemini-3.7-flash_lowGoogle DeepMind | closed | effort low | 5.7% | not dated | via Epoch AI |
| 144 | grok-4.6_lowxAI | closed | effort low | 5.7% | not dated | via Epoch AI |
| 145 | thinkingmachines/InklingEpoch: Inkling_xhigh, Thinking Machines | open | effort xhigh | 5.4% | not dated | via Epoch AI |
| 146 | Qwen/Qwen3.8-27BEpoch: qwen3.8-27b_xhigh, Alibaba | open | effort xhigh | 5.4% | not dated | via Epoch AI |
| 147 | gpt-5.6-sol_noneOpenAI | closed | effort none | 5.1% | not dated | via Epoch AI |
| 148 | gpt-5.1-2025-11-13_unknownOpenAI | closed | effort unknown | 4.9% | not dated | via Epoch AI |
| 149 | gpt-5.6-luna_mediumOpenAI | closed | effort medium | 4.9% | not dated | via Epoch AI |
| 150 | gpt-6.1-terra_noneOpenAI | closed | effort none | 4.9% | not dated | via Epoch AI |
| 151 | claude-sonnet-5_lowAnthropic | closed | effort low | 4.6% | not dated | via Epoch AI |
| 152 | zai-org/GLM-5.1Epoch: glm-5.1, Z.ai (Zhipu AI) | open | default | 4.6% | not dated | via Epoch AI |
| 153 | gemini-3.8-flash_lowGoogle DeepMind | closed | effort low | 4.0% | not dated | via Epoch AI |
| 154 | gpt-6-sol_noneOpenAI | closed | effort none | 4.0% | not dated | via Epoch AI |
| 155 | XiaomiMiMo/MiMo-V2.5-ProEpoch: mimo-v2.5-pro, Xiaomi Corp | open | default | 4.0% | not dated | via Epoch AI |
| 156 | XiaomiMiMo/MiMo-V2.5Epoch: mimo-v2.5, Xiaomi Corp | open | default | 3.7% | not dated | via Epoch AI |
| 157 | MiniMaxAI/MiniMax-M3Epoch: MiniMax-M3, MiniMax | open | default | 3.7% | not dated | via Epoch AI |
| 158 | inclusionAI/Ring-2.6-1TEpoch: Ring-2.6-1T, Ant Group | open | default | 3.7% | not dated | via Epoch AI |
| 159 | deepseek-ai/DeepSeek-V4-FlashEpoch: deepseek-v4-flash_high, DeepSeek | open | effort high | 3.4% | not dated | via Epoch AI |
| 160 | claude-sonnet-4-6_maxAnthropic | closed | effort max | 3.1% | not dated | via Epoch AI |
| 161 | zai-org/GLM-5.2Epoch: glm-5.2_none, Z.ai (Zhipu AI) | open | effort none | 3.1% | not dated | via Epoch AI |
| 162 | moonshotai/Kimi-K2.5Epoch: kimi-k2.5, Moonshot | open | default | 3.1% | not dated | via Epoch AI |
| 163 | moonshotai/Kimi-K3Epoch: kimi-k3_low, Moonshot | open | effort low | 3.1% | not dated | via Epoch AI |
| 164 | nemotron-3-superNvidiano page match | open | default | 3.1% | not dated | via Epoch AI |
| 165 | nemotron-3-ultraNvidiano page match | open | default | 3.1% | not dated | via Epoch AI |
| 166 | deepseek-ai/DeepSeek-V3.2-ExpEpoch: DeepSeek-V3.2-Exp_thinking, DeepSeek | open | effort thinking | 2.9% | not dated | via Epoch AI |
| 167 | qwen3.6-plusAlibaba | closed | default | 2.9% | not dated | via Epoch AI |
| 168 | gpt-5.6-luna_lowOpenAI | closed | effort low | 2.6% | not dated | via Epoch AI |
| 169 | gpt-6-luna_lowOpenAI | closed | effort low | 2.6% | not dated | via Epoch AI |
| 170 | muse-glimmer_highMeta AIno page match | open | effort high | 2.6% | not dated | via Epoch AI |
| 171 | stepfun-ai/Step-3.7-FlashEpoch: step-3.7-flash, StepFun | open | default | 2.3% | not dated | via Epoch AI |
| 172 | gemini-2.5-proGoogle DeepMind | closed | default | 2.0% | not dated | via Epoch AI |
| 173 | gpt-5.6-terra_noneOpenAI | closed | effort none | 2.0% | not dated | via Epoch AI |
| 174 | deepseek-ai/DeepSeek-V3.1-TerminusEpoch: DeepSeek-V3.1-Terminus, DeepSeek | open | default | 1.7% | not dated | via Epoch AI |
| 175 | zai-org/GLM-4.7Epoch: glm-4.7, Z.ai (Zhipu AI) | open | default | 1.7% | not dated | via Epoch AI |
| 176 | google/gemma-4-31B-itEpoch: gemma-4-31b-it, Google DeepMind | open | default | 1.4% | not dated | via Epoch AI |
| 177 | gpt-5.5_noneOpenAI | closed | effort none | 1.4% | not dated | via Epoch AI |
| 178 | openai/gpt-oss-20bEpoch: gpt-oss-20b_high, OpenAI | open | effort high | 1.4% | not dated | via Epoch AI |
| 179 | claude-sonnet-4-5-20250929_unknownAnthropic | closed | effort unknown | 1.1% | not dated | via Epoch AI |
| 180 | claude-sonnet-5_highAnthropic | closed | effort high | 1.1% | not dated | via Epoch AI |
| 181 | gemini-3.1-flash-liteGoogle | closed | default | 1.1% | not dated | via Epoch AI |
| 182 | zai-org/GLM-4.6Epoch: glm-4.6, Z.ai (Zhipu AI),Tsinghua University | open | default | 1.1% | not dated | via Epoch AI |
| 183 | gpt-6-luna_noneOpenAI | closed | effort none | 1.1% | not dated | via Epoch AI |
| 184 | o3-2025-04-16_highOpenAI | closed | effort high | 1.1% | not dated | via Epoch AI |
| 185 | openai/gpt-oss-120bEpoch: openai/gpt-oss-120b_high, OpenAI | open | effort high | 1.1% | not dated | via Epoch AI |
| 186 | deepseek-ai/DeepSeek-R1Epoch: DeepSeek-R1, DeepSeek | open | default | 1.1% | not dated | via Epoch AI |
| 187 | gemini-2.5-flashGoogle DeepMind | closed | default | 1.1% | not dated | via Epoch AI |
| 188 | Qwen/Qwen3.5-122B-A10BEpoch: qwen3.5-122b-a10b_none, Alibaba | open | effort none | 0.9% | not dated | via Epoch AI |
| 189 | Qwen/Qwen3.5-397B-A17BEpoch: qwen3.5-397b-a17b_none, Alibaba | open | effort none | 0.9% | not dated | via Epoch AI |
| 190 | Qwen/Qwen3.6-27BEpoch: qwen3.6-27b_none, Alibaba | open | effort none | 0.9% | not dated | via Epoch AI |
| 191 | trinity-large-thinkingArcee AIno page match | open | default | 0.9% | not dated | via Epoch AI |
| 192 | mercury-2Inception Labs | closed | default | 0.8% | not dated | via Epoch AI |
| 193 | o4-mini-2025-04-16_highOpenAI | closed | effort high | 0.6% | not dated | via Epoch AI |
| 194 | MiniMaxAI/MiniMax-M2.7Epoch: MiniMax-M2.7, MiniMax | open | default | 0.6% | not dated | via Epoch AI |
| 195 | Qwen/Qwen3.5-35B-A3BEpoch: qwen3.5-35b-a3b_none, Alibaba | open | effort none | 0.6% | not dated | via Epoch AI |
| 196 | Qwen/Qwen3.5-9BEpoch: qwen3.5-9B_none, Alibaba | open | effort none | 0.6% | not dated | via Epoch AI |
| 197 | claude-opus-4-20250514_unknownAnthropic | closed | effort unknown | 0.3% | not dated | via Epoch AI |
| 198 | claude-sonnet-4-20250514_unknownAnthropic | closed | effort unknown | 0.3% | not dated | via Epoch AI |
| 199 | command-a-plus-05-2026Cohere,Cohere Labs (formerly Cohere for AI)no page match | open | default | 0.3% | not dated | via Epoch AI |
| 200 | deepseek-ai/DeepSeek-V4.1-FlashEpoch: deepseek-v4.1-flash_none, DeepSeek | open | effort none | 0.3% | not dated | via Epoch AI |
| 201 | deepseek-ai/DeepSeek-V4.1-Flash-1017Epoch: deepseek-v4.1-flash-1017_none, DeepSeek | open | effort none | 0.3% | not dated | via Epoch AI |
| 202 | gpt-5.6-luna_noneOpenAI | closed | effort none | 0.3% | not dated | via Epoch AI |
| 203 | magistral-medium-2509Mistral AI | closed | default | 0.3% | not dated | via Epoch AI |
| 204 | mistralai/Magistral-Small-2509Epoch: magistral-small-2509, Mistral AI | open | default | 0.3% | not dated | via Epoch AI |
| 205 | o3-mini-2025-01-31_highOpenAI | closed | effort high | 0.3% | not dated | via Epoch AI |
| 206 | Qwen/Qwen3-30B-A3B-Thinking-2507Epoch: qwen3-30b-a3b-thinking-2507, Alibaba | open | default | 0.3% | not dated | via Epoch AI |
| 207 | Qwen/Qwen3-32BEpoch: Qwen3-32B, Alibaba | open | default | 0.3% | not dated | via Epoch AI |
| 208 | Qwen/Qwen3.5-9BEpoch: qwen3.5-9B, Alibaba | open | default | 0.3% | not dated | via Epoch AI |
| 209 | Qwen/Qwen3.6-35B-A3BEpoch: qwen3.6-35b-a3b, Alibaba | open | default | 0.3% | not dated | via Epoch AI |
| 210 | Qwen/Qwen3.8-27BEpoch: qwen3.8-27b_none, Alibaba | open | effort none | 0.3% | not dated | via Epoch AI |
| 211 | amazon.nova-micro-v1:0Amazon | closed | default | 0.0% | not dated | via Epoch AI |
| 212 | CohereLabs/c4ai-command-a-03-2025Epoch: c4ai-command-a-03-2025, Cohere | open | default | 0.0% | not dated | via Epoch AI |
| 213 | meta-llama/Llama-4-Maverick-17B-128E-InstructEpoch: chutes/Llama-4-Maverick-17B-128E-Instruct, Meta AI | open | default | 0.0% | not dated | via Epoch AI |
| 214 | claude-3-5-haiku-20241022Anthropic | closed | default | 0.0% | not dated | via Epoch AI |
| 215 | claude-haiku-4-5-20251001_unknownAnthropic | closed | effort unknown | 0.0% | not dated | via Epoch AI |
| 216 | cogito-671b-v2.1Deep Cogitono page match | open | default | 0.0% | not dated | via Epoch AI |
| 217 | deepseek-ai/DeepSeek-V3Epoch: DeepSeek-V3, DeepSeek | open | default | 0.0% | not dated | via Epoch AI |
| 218 | deepseek-ai/DeepSeek-V3-0324Epoch: DeepSeek-V3-0324, DeepSeek | open | default | 0.0% | not dated | via Epoch AI |
| 219 | deepseek-ai/DeepSeek-V4-Pro-0813Epoch: deepseek-v4-pro-0813_none, DeepSeek | open | effort none | 0.0% | not dated | via Epoch AI |
| 220 | devstral-small-2512Mistral AIno page match | open | default | 0.0% | not dated | via Epoch AI |
| 221 | gemini-3.5-flash-liteGoogle DeepMind | closed | default | 0.0% | not dated | via Epoch AI |
| 222 | google/gemma-3-12b-itEpoch: gemma-3-12b-it, Google DeepMind | open | default | 0.0% | not dated | via Epoch AI |
| 223 | google/gemma-3-270m-itEpoch: gemma-3-270m-it, Google DeepMind | open | default | 0.0% | not dated | via Epoch AI |
| 224 | google/gemma-3-27b-itEpoch: gemma-3-27b-it, Google DeepMind | open | default | 0.0% | not dated | via Epoch AI |
| 225 | gemma-4-26b-a4bGoogle DeepMindno page match | open | default | 0.0% | not dated | via Epoch AI |
| 226 | gpt-4.1-mini-2025-04-14OpenAI | closed | default | 0.0% | not dated | via Epoch AI |
| 227 | gpt-4.1-nano-2025-04-14OpenAI | closed | default | 0.0% | not dated | via Epoch AI |
| 228 | gpt-4o-2024-11-20OpenAI | closed | default | 0.0% | not dated | via Epoch AI |
| 229 | gpt-5-2025-08-07_minimalOpenAI | closed | effort minimal | 0.0% | not dated | via Epoch AI |
| 230 | gpt-5-mini-2025-08-07_highOpenAI | closed | effort high | 0.0% | not dated | via Epoch AI |
| 231 | gpt-5-mini-2025-08-07_unknownOpenAI | closed | effort unknown | 0.0% | not dated | via Epoch AI |
| 232 | gpt-5.5-instantOpenAI | closed | default | 0.0% | not dated | via Epoch AI |
| 233 | openai/gpt-oss-20bEpoch: gpt-oss-20b_low, OpenAI | open | effort low | 0.0% | not dated | via Epoch AI |
| 234 | ibm-granite/granite-4.0-350mEpoch: granite-4.0-350m | open | default | 0.0% | not dated | via Epoch AI |
| 235 | ibm-granite/granite-4.0-microEpoch: granite-4.0-micro | open | default | 0.0% | not dated | via Epoch AI |
| 236 | ibm-granite/granite-4.1-30bEpoch: granite-4.1-30b, IBM | open | default | 0.0% | not dated | via Epoch AI |
| 237 | grok-4.3_nonexAI | closed | effort none | 0.0% | not dated | via Epoch AI |
| 238 | grok-4.3_unknownxAI | closed | effort unknown | 0.0% | not dated | via Epoch AI |
| 239 | meta-llama/Llama-3.1-405B-InstructEpoch: Llama-3.1-405B-Instruct, Meta AI | open | default | 0.0% | not dated | via Epoch AI |
| 240 | meta-llama/Llama-3.1-8B-InstructEpoch: Llama-3.1-8B-Instruct, Meta AI | open | default | 0.0% | not dated | via Epoch AI |
| 241 | meta-llama/Llama-3.2-11B-Vision-InstructEpoch: Llama-3.2-11B-Vision-Instruct, Meta AI | open | default | 0.0% | not dated | via Epoch AI |
| 242 | meta-llama/Llama-3.3-70B-InstructEpoch: Llama-3.3-70B-Instruct, Meta AI | open | default | 0.0% | not dated | via Epoch AI |
| 243 | meta-llama/Llama-4-Maverick-17B-128E-InstructEpoch: Llama-4-Maverick-17B-128E-Instruct, Meta AI | open | default | 0.0% | not dated | via Epoch AI |
| 244 | meta-llama/Llama-4-Scout-17B-16E-InstructEpoch: Llama-4-Scout-17B-16E-Instruct, Meta AI | open | default | 0.0% | not dated | via Epoch AI |
| 245 | mercury-2.5_unknownInception Labs | closed | effort unknown | 0.0% | not dated | via Epoch AI |
| 246 | XiaomiMiMo/MiMo-V2-FlashEpoch: mimo-v2-flash, Xiaomi Corp | open | default | 0.0% | not dated | via Epoch AI |
| 247 | mistral-large-2512Mistral AIno page match | open | default | 0.0% | not dated | via Epoch AI |
| 248 | mistral-medium-2508Mistral AI | closed | default | 0.0% | not dated | via Epoch AI |
| 249 | mistral-medium-2604Mistral AIno page match | open | default | 0.0% | not dated | via Epoch AI |
| 250 | mistral-small-2503Mistral AIno page match | open | default | 0.0% | not dated | via Epoch AI |
| 251 | mistral-small-2506Mistral AIno page match | open | default | 0.0% | not dated | via Epoch AI |
| 252 | nova-2.0-pro-preview_lowAmazon | closed | effort low | 0.0% | not dated | via Epoch AI |
| 253 | nova-2.0-pro-preview_mediumAmazon | closed | effort medium | 0.0% | not dated | via Epoch AI |
| 254 | nova-2.0-pro-preview_noneAmazon | closed | effort none | 0.0% | not dated | via Epoch AI |
| 255 | nvidia/NVIDIA-Nemotron-Nano-9B-v2Epoch: nvidia-nemotron-nano-9b-v2 | open | default | 0.0% | not dated | via Epoch AI |
| 256 | openai/gpt-oss-120bEpoch: openai/gpt-oss-120b_low, OpenAI | open | effort low | 0.0% | not dated | via Epoch AI |
| 257 | microsoft/phi-4Epoch: phi-4, Microsoft Research | open | default | 0.0% | not dated | via Epoch AI |
| 258 | microsoft/Phi-4-mini-instructEpoch: Phi-4-mini-instruct, Microsoft | open | default | 0.0% | not dated | via Epoch AI |
| 259 | Qwen/Qwen3-235B-A22B-Thinking-2507Epoch: qwen/qwen3-235b-a22b-thinking-2507, Alibaba | open | default | 0.0% | not dated | via Epoch AI |
| 260 | Qwen/Qwen3-14BEpoch: qwen3-14b, Alibaba | open | default | 0.0% | not dated | via Epoch AI |
| 261 | Qwen/Qwen3-8BEpoch: qwen3-8b, Alibaba | open | default | 0.0% | not dated | via Epoch AI |
| 262 | Qwen/Qwen3-Coder-NextEpoch: qwen3-coder-next | open | default | 0.0% | not dated | via Epoch AI |
| 263 | Qwen/Qwen3.5-0.8BEpoch: qwen3.5-0.8b, Alibaba | open | default | 0.0% | not dated | via Epoch AI |
| 264 | Qwen/Qwen3.5-0.8BEpoch: qwen3.5-0.8b_none, Alibaba | open | effort none | 0.0% | not dated | via Epoch AI |
| 265 | Qwen/Qwen3.5-2BEpoch: qwen3.5-2b_none, Alibaba | open | effort none | 0.0% | not dated | via Epoch AI |
| 266 | Qwen/Qwen3.5-4BEpoch: qwen3.5-4b_none, Alibaba | open | effort none | 0.0% | not dated | via Epoch AI |
| 267 | Qwen/Qwen3.6-35B-A3BEpoch: qwen3.6-35b-a3b_none, Alibaba | open | effort none | 0.0% | not dated | via Epoch AI |
| 268 | Qwen/Qwen3.8-27BEpoch: qwen3.8-27b_low, Alibaba | open | effort low | 0.0% | not dated | via Epoch AI |
| 269 | Qwen/Qwen3.8-27BEpoch: qwen3.8-27b_medium, Alibaba | open | effort medium | 0.0% | not dated | via Epoch AI |
| 270 | RekaAI/reka-flash-3Epoch: reka-flash-3, Reka AI | open | default | 0.0% | not dated | via Epoch AI |
| 271 | solar-pro-3Upstage | closed | default | 0.0% | not dated | via Epoch AI |
Open-weight rows are shaded. Dates are when the result was run or evaluated, where the data says. Data from Epoch AI (CC-BY 4.0), fetched 19 Nov 2026: Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from ‘https://epoch.ai/benchmarks’ [online resource]. Epoch AI. Method