SimpleQA Verified
Re-run by Epoch AINo description yet: we only describe an eval set when we can do it correctly.
- Kind
- Run independently by Epoch AI, with public logs. Our own re-runs are not built yet.
- Score shown
- Epoch's column "Best score (across scorers)", as a percentage, higher is better; random guessing scores about 0.0%. Error bars as the source gives them.
- Results
- 105 in all: 21 for open-weight models, 80 for closed ones, 4 where Epoch does not say. 19 linked to a model page here.
Best open-weight result: moonshotai/Kimi-K3.1-Pro, 62.2%, number 19 of 105 results.
| # | Model | Weights | Setting | Score | Date | Source |
|---|---|---|---|---|---|---|
| 1 | claude-fable-5-2_maxAnthropic | closed | effort max | 94.0%±0.8 | 6 Nov 2026 | Epoch AI |
| 2 | gpt-6.2-astra_maxOpenAI | closed | effort max | 78.5%±1.3 | 27 Oct 2026 | Epoch AI |
| 3 | gemini-4-carbon_highGoogle DeepMind | closed | effort high | 77.7%±1.3 | 2 Nov 2026 | Epoch AI |
| 4 | gemini-4-argon_highGoogle DeepMind | closed | effort high | 76.0%±1.4 | 13 Oct 2026 | Epoch AI log |
| 5 | gpt-6-astra_maxOpenAI | closed | effort max | 75.6%±1.4 | 30 Aug 2026 | Epoch AI log |
| 6 | gpt-6.1-sol_maxOpenAI | closed | effort max | 73.9%±1.4 | 29 Sep 2026 | Epoch AI log |
| 7 | gemini-3.1-pro-preview_highGoogle DeepMind | closed | effort high | 73.5%±1.4 | 10 Aug 2026 | Epoch AI |
| 8 | claude-opus-5-5_maxAnthropic | closed | effort max | 72.2%±1.4 | 22 Sep 2026 | Epoch AI log |
| 9 | gemini-4-hydrogen_xhighGoogle DeepMind | closed | effort xhigh | 70.9%±1.4 | 13 Nov 2026 | Epoch AI log |
| 10 | claude-fable-5-1_maxAnthropic | closed | effort max | 70.8%±1.4 | 1 Sep 2026 | Epoch AI log |
| 11 | claude-fable-5_xhighAnthropic | closed | effort xhigh | 70.7%±1.4 | 10 Aug 2026 | Epoch AI |
| 12 | gemini-3.8-flash_highGoogle DeepMind | closed | effort high | 69.7%±1.5 | 2 Sep 2026 | Epoch AI log |
| 13 | gpt-5.6-sol_maxOpenAI | closed | effort max | 69.7%±1.5 | 10 Aug 2026 | Epoch AI |
| 14 | gemini-3.7-flash_highGoogle DeepMind | closed | effort high | 69.2%±1.5 | 27 Aug 2026 | Epoch AI log |
| 15 | gemini-3-flash-preview_highGoogle DeepMind | closed | effort high | 66.8%±1.5 | 27 Aug 2026 | Epoch AI log |
| 16 | gemini-3.5-flash_highGoogle DeepMind | closed | effort high | 66.2%±1.5 | 27 Aug 2026 | Epoch AI log |
| 17 | gemini-3.6-flash_highGoogle DeepMind | closed | effort high | 66.2%±1.5 | 27 Aug 2026 | Epoch AI log |
| 18 | gpt-5.5_xhighOpenAI | closed | effort xhigh | 63.0%±1.5 | 27 Aug 2026 | Epoch AI log |
| 19 | moonshotai/Kimi-K3.1-ProEpoch: kimi-k3.1-pro-together_max, Moonshot | open | effort max | 62.2%±1.5 | 6 Nov 2026 | Epoch AI log |
| 20 | gpt-6-sol_maxOpenAI | closed | effort max | 60.7%±1.5 | 22 Sep 2026 | Epoch AI log |
| 21 | muse-spark-1.2_xhighMeta AI | closed | effort xhigh | 60.3%±1.6 | 27 Aug 2026 | Epoch AI log |
| 22 | claude-opus-5_maxAnthropic | closed | effort max | 59.9%±1.6 | 10 Aug 2026 | Epoch AI |
| 23 | muse-spark-1.1Meta AI | closed | default | 57.8%±1.6 | 31 Aug 2026 | Epoch AI log |
| 24 | gpt-6.1-terra_maxOpenAI | closed | effort max | 57.3%±1.6 | 26 Oct 2026 | Epoch AI log |
| 25 | meta-models/Muse-Spark-Open-816B-A42BEpoch: Muse-Spark-Open-816B-A42B_xhigh, Meta AI | open | effort xhigh | 56.6%±1.6 | 15 Oct 2026 | Epoch AI log |
| 26 | grok-4.7_xhighxAI | closed | effort xhigh | 56.0%±1.6 | 22 Sep 2026 | Epoch AI log |
| 27 | qwen3.7-maxAlibaba | closed | default | 55.8%±1.6 | 27 Aug 2026 | Epoch AI log |
| 28 | claude-opus-4-8_maxAnthropic | closed | effort max | 53.0%±1.6 | 27 Aug 2026 | Epoch AI log |
| 29 | deepseek-ai/DeepSeek-V4-Pro-0813Epoch: deepseek-v4-pro-0813_max, DeepSeek | open | effort max | 52.9%±1.6 | 27 Aug 2026 | Epoch AI log |
| 30 | qwen3.6-max-previewAlibaba | not stated | default | 52.0%±1.6 | 27 Aug 2026 | Epoch AI log |
| 31 | claude-opus-4-7_xhighAnthropic | closed | effort xhigh | 51.7%±1.6 | 27 Aug 2026 | Epoch AI log |
| 32 | moonshotai/Kimi-K3Epoch: kimi-k3_max, Moonshot | open | effort max | 50.6%±1.6 | 27 Aug 2026 | Epoch AI log |
| 33 | gpt-5-2025-08-07_highOpenAI | closed | effort high | 50.1%±1.6 | 27 Aug 2026 | Epoch AI log |
| 34 | o3-2025-04-16_highOpenAI | closed | effort high | 49.4%±1.6 | 27 Aug 2026 | Epoch AI log |
| 35 | grok-4.6_highxAI | closed | effort high | 49.3%±1.6 | 27 Aug 2026 | Epoch AI log |
| 36 | grok-4.6_xhighxAI | closed | effort xhigh | 48.9%±1.6 | 27 Aug 2026 | Epoch AI log |
| 37 | qwen3-max-2025-09-23Alibaba | closed | default | 48.7%±1.6 | 27 Aug 2026 | Epoch AI log |
| 38 | grok-4.5_highxAI | closed | effort high | 48.3%±1.6 | 27 Aug 2026 | Epoch AI log |
| 39 | gpt-5.1-2025-11-13_highOpenAI | closed | effort high | 48.0%±1.6 | 27 Aug 2026 | Epoch AI log |
| 40 | qwen3.8-max-0902_xhighAlibaba | closed | effort xhigh | 47.3%±1.6 | 2 Sep 2026 | Epoch AI log |
| 41 | claude-opus-4-6_maxAnthropic | closed | effort max | 47.0%±1.6 | 27 Aug 2026 | Epoch AI log |
| 42 | deepseek-ai/DeepSeek-V4-ProEpoch: deepseek-v4-pro_max, DeepSeek | open | effort max | 47.0%±1.6 | 27 Aug 2026 | Epoch AI log |
| 43 | claude-sonnet-5-5_maxAnthropic | closed | effort max | 46.5%±1.6 | 29 Sep 2026 | Epoch AI log |
| 44 | gpt-5.4-pro-2026-03-05_xhighOpenAI | closed | effort xhigh | 46.3%±1.6 | 27 Aug 2026 | Epoch AI log |
| 45 | qwen3.8-max_xhighAlibaba | closed | effort xhigh | 45.8%±1.6 | 27 Aug 2026 | Epoch AI log |
| 46 | claude-opus-4-5-20251101_32KAnthropic | closed | default | 45.7%±1.6 | 27 Aug 2026 | Epoch AI log |
| 47 | gpt-5.4-2026-03-05_xhighOpenAI | closed | effort xhigh | 45.1%±1.6 | 27 Aug 2026 | Epoch AI log |
| 48 | doubao-seed-2.1-pro-260628_highByteDance | closed | effort high | 44.7%±1.6 | 28 Oct 2026 | Epoch AI log |
| 49 | qwen3.6-plusAlibaba | closed | default | 44.1%±1.6 | 27 Aug 2026 | Epoch AI log |
| 50 | gpt-5.6-terra_maxOpenAI | closed | effort max | 43.2%±1.6 | 10 Aug 2026 | Epoch AI |
| 51 | deepseek-ai/DeepSeek-V4.1-FlashEpoch: deepseek-v4.1-flash_max, DeepSeek | open | effort max | 42.9%±1.6 | 13 Oct 2026 | Epoch AI log |
| 52 | deepseek-ai/DeepSeek-V4.1-Flash-1017Epoch: deepseek-v4.1-flash-1017_max, DeepSeek | open | effort max | 42.5%±1.6 | 19 Oct 2026 | Epoch AI log |
| 53 | doubao-seed-evolving_highByteDance | closed | effort high | 41.9%±1.6 | 2 Nov 2026 | Epoch AI log |
| 54 | gpt-6-luna_maxOpenAI | closed | effort max | 41.4%±1.6 | 22 Sep 2026 | Epoch AI log |
| 55 | o1-2024-12-17_highOpenAI | closed | effort high | 41.1%±1.6 | 31 Aug 2026 | Epoch AI log |
| 56 | zai-org/GLM-5.3Epoch: glm-5.3_max, Z.ai (Zhipu AI) | open | effort max | 41.0%±1.6 | 28 Aug 2026 | Epoch AI log |
| 57 | gpt-5.6-luna_maxOpenAI | closed | effort max | 41.0%±1.6 | 10 Aug 2026 | Epoch AI |
| 58 | Qwen/Qwen3-235B-A22B-Thinking-2507Epoch: Qwen3-235B-A22B-Thinking-2507, Alibaba | open | default | 40.4%±1.6 | 27 Aug 2026 | Epoch AI log |
| 59 | thinkingmachines/InklingEpoch: Inkling_xhigh, Thinking Machines | open | effort xhigh | 40.3%±1.6 | 27 Aug 2026 | Epoch AI log |
| 60 | doubao-seed-2.0-pro-260215_highByteDance | closed | effort high | 39.4%±1.5 | 28 Oct 2026 | Epoch AI log |
| 61 | gpt-5.2-2025-12-11_xhighOpenAI | closed | effort xhigh | 37.1%±1.5 | 27 Aug 2026 | Epoch AI log |
| 62 | moonshotai/Kimi-K2.7-CodeEpoch: kimi-k2.7-code, Moonshot | open | default | 36.5%±1.5 | 27 Aug 2026 | Epoch AI log |
| 63 | claude-sonnet-4-6_highAnthropic | closed | effort high | 35.5%±1.5 | 10 Aug 2026 | Epoch AI |
| 64 | moonshotai/Kimi-K2.6Epoch: kimi-k2.6, Moonshot | open | default | 34.9%±1.5 | 10 Aug 2026 | Epoch AI |
| 65 | gpt-5.2-2025-12-11_highOpenAI | closed | effort high | 34.3%±1.5 | 27 Aug 2026 | Epoch AI log |
| 66 | moonshotai/Kimi-K2.5Epoch: kimi-k2.5, Moonshot | open | default | 34.3%±1.5 | 27 Aug 2026 | Epoch AI log |
| 67 | zai-org/GLM-5.2Epoch: glm-5.2_max, Z.ai (Zhipu AI) | open | effort max | 34.2%±1.5 | 27 Aug 2026 | Epoch AI log |
| 68 | zai-org/GLM-5.1Epoch: glm-5.1, Z.ai (Zhipu AI) | open | default | 34.0%±1.5 | 27 Aug 2026 | Epoch AI log |
| 69 | claude-sonnet-5_maxAnthropic | closed | effort max | 33.7%±1.5 | 27 Aug 2026 | Epoch AI log |
| 70 | deepseek-ai/DeepSeek-V4-Flash-0731Epoch: deepseek-v4-flash-0731_max, DeepSeek | open | effort max | 33.6%±1.5 | 27 Aug 2026 | Epoch AI log |
| 71 | grok-4.3_highxAI | closed | effort high | 33.2%±1.5 | 27 Aug 2026 | Epoch AI log |
| 72 | claude-sonnet-5_xhighAnthropic | closed | effort xhigh | 32.9%±1.5 | 27 Aug 2026 | Epoch AI log |
| 73 | claude-sonnet-4-6_maxAnthropic | closed | effort max | 32.8%±1.5 | 27 Aug 2026 | Epoch AI log |
| 74 | gpt-5.2-2025-12-11_lowOpenAI | closed | effort low | 32.8%±1.5 | 27 Aug 2026 | Epoch AI log |
| 75 | gpt-5.2-2025-12-11_mediumOpenAI | closed | effort medium | 32.7%±1.5 | 27 Aug 2026 | Epoch AI log |
| 76 | zai-org/GLM-4.7Epoch: glm-4.7, Z.ai (Zhipu AI) | open | default | 32.2%±1.5 | 27 Aug 2026 | Epoch AI log |
| 77 | doubao-seed-2.0-lite-260428_highByteDance | closed | effort high | 31.5%±1.5 | 28 Oct 2026 | Epoch AI log |
| 78 | gpt-4.1-2025-04-14OpenAI | closed | default | 31.1%±1.5 | 31 Aug 2026 | Epoch AI log |
| 79 | claude-sonnet-4-5-20250929_59KAnthropic | closed | default | 30.7%±1.5 | 27 Aug 2026 | Epoch AI log |
| 80 | grok-4.20-0309-reasoningxAI | closed | default | 30.2%±1.5 | 27 Aug 2026 | Epoch AI log |
| 81 | doubao-seed-2.1-turbo-260628_highByteDance | closed | effort high | 29.7%±1.4 | 30 Oct 2026 | Epoch AI log |
| 82 | gpt-5.4-mini-2026-03-17_highOpenAI | closed | effort high | 29.4%±1.4 | 27 Aug 2026 | Epoch AI log |
| 83 | gpt-4o-2024-08-06OpenAI | closed | default | 26.0%±1.4 | 31 Aug 2026 | Epoch AI log |
| 84 | qwen3.5-plusAlibaba | not stated | default | 25.4%±1.4 | 27 Aug 2026 | Epoch AI log |
| 85 | claude-haiku-5-5_maxAnthropic | closed | effort max | 23.8%±1.3 | 9 Oct 2026 | Epoch AI log |
| 86 | claude-sonnet-4-5-20250929Anthropic | closed | default | 23.7%±1.3 | 10 Aug 2026 | Epoch AI |
| 87 | mistral-large-4-0-oss_highMistral AIno page match | open | effort high | 22.4%±1.3 | 2 Nov 2026 | Epoch AI log |
| 88 | gpt-5-mini-2025-08-07_highOpenAI | closed | effort high | 21.6%±1.3 | 10 Aug 2026 | Epoch AI |
| 89 | qwen3.5-flashAlibaba | not stated | default | 20.3%±1.3 | 27 Aug 2026 | Epoch AI log |
| 90 | mistral-large-4-0_highMistral AIno page match | open | effort high | 20.0%±1.3 | 9 Oct 2026 | Epoch AI log |
| 91 | o4-mini-2025-04-16_lowOpenAI | closed | effort low | 19.6%±1.3 | 27 Aug 2026 | Epoch AI log |
| 92 | thinkingmachines/Inkling-SmallEpoch: inkling-small_xhigh, Thinking Machines | open | effort xhigh | 19.1%±1.2 | 27 Aug 2026 | Epoch AI log |
| 93 | o4-mini-2025-04-16_highOpenAI | closed | effort high | 18.8%±1.2 | 27 Aug 2026 | Epoch AI log |
| 94 | seed-1.6ByteDance | closed | default | 17.4%±1.2 | 30 Oct 2026 | Epoch AI log |
| 95 | qwen3.6-flashAlibaba | not stated | default | 15.9%±1.2 | 27 Aug 2026 | Epoch AI log |
| 96 | o3-mini-2025-01-31_highOpenAI | closed | effort high | 15.3%±1.1 | 31 Aug 2026 | Epoch AI log |
| 97 | claude-haiku-4-5-20251001Anthropic | closed | default | 13.2%±1.1 | 10 Aug 2026 | Epoch AI |
| 98 | gpt-4.1-mini-2025-04-14OpenAI | closed | default | 12.7%±1.1 | 31 Aug 2026 | Epoch AI log |
| 99 | claude-3-opus-20240229Anthropic | closed | default | 12.6%±1.0 | 31 Aug 2026 | Epoch AI log |
| 100 | claude-haiku-4-5-20251001_32KAnthropic | closed | default | 12.6%±1.0 | 27 Aug 2026 | Epoch AI log |
| 101 | gpt-5-nano-2025-08-07_highOpenAI | closed | effort high | 11.7%±1.0 | 10 Aug 2026 | Epoch AI |
| 102 | gpt-5.4-nano-2026-03-17_highOpenAI | closed | effort high | 11.7%±1.0 | 27 Aug 2026 | Epoch AI log |
| 103 | google/gemma-4-31B-itEpoch: gemma-4-31b-it, Google DeepMind | open | default | 10.4%±1.0 | 27 Aug 2026 | Epoch AI log |
| 104 | gpt-4o-mini-2024-07-18OpenAI | closed | default | 8.3%±0.9 | 31 Aug 2026 | Epoch AI log |
| 105 | gpt-4.1-nano-2025-04-14OpenAI | closed | default | 6.0%±0.8 | 31 Aug 2026 | Epoch AI log |
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