Updated daily at 05:00 UTC
Benchmark
Chess Puzzles
Measures: 100 novel chess positions generated with the Stockfish engine, given as FEN text; the model must name the single best next move.
- Maintainer
- Epoch AI
- Introduced
- 2025
- Status
- Active
- Saturation
- Headroom
- Typical provenance
- Independent
- In scoring set
- Yes
Leaderboard
Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.
| Model | Puzzles solved | Provenance | Source | Evaluated |
|---|---|---|---|---|
| DeepSeek LLM 67B Chat | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| DeepSeek-R1-Distill-Qwen-1.5B | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| Gemma 3 12B | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| Gemma 3 1B | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| Gemma 3 27B | 0.0% | Independent | Epoch AI | 27 Aug 2026 |
| Gemma 3 4B | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| GLM-4.7-Flash Z.ai (Zhipu AI) · None effort | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| GLM-4.7-Flash | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| GPT-3.5 Turbo | 0.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-4o mini | 0.0% | Independent | Epoch AI | 15 Jul 2026 |
| gpt-oss-20b OpenAI · High effort | 0.0% | Independent | Epoch AI | 27 Aug 2026 |
| Granite 4.0 1B (Nano) | 0.0% | Independent | Epoch AI | 30 Aug 2026 |
| Granite 4.0 350M (Nano) | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| Granite 4.0 Micro (3B) | 0.0% | Independent | Epoch AI | 30 Aug 2026 |
| Llama 3 8B | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| Llama 3.1 8B | 0.0% | Independent | Epoch AI | 27 Aug 2026 |
| Llama 3.2 1B | 0.0% | Independent | Epoch AI | 30 Aug 2026 |
| Mistral 7B v0.3 | 0.0% | Independent | Epoch AI | 30 Aug 2026 |
| Qwen2.5-32B-Instruct | 0.0% | Independent | Epoch AI | 30 Aug 2026 |
| Qwen2.5-7B-Instruct | 0.0% | Independent | Epoch AI | 30 Aug 2026 |
| Qwen3-1.7B Alibaba Group · None effort | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| Qwen3-14B Alibaba Group · None effort | 0.0% | Independent | Epoch AI | 30 Aug 2026 |
| Qwen3-8B Alibaba Group · None effort | 0.0% | Independent | Epoch AI | 27 Aug 2026 |
| Qwen3.5-2B Alibaba Group · None effort | 0.0% | Independent | Epoch AI | 28 Aug 2026 |
| DeepSeek-R1-Distill-Qwen-14B | 1.0% | Independent | Epoch AI | 28 Aug 2026 |
| DeepSeek-R1-Distill-Qwen-32B | 1.0% | Independent | Epoch AI | 28 Aug 2026 |
| DeepSeek-V3.2 | 1.0% | Independent | Epoch AI | 16 Jul 2026 |
| GPT-5 nano OpenAI · Minimal effort | 1.0% | Independent | Epoch AI | 13 Jul 2026 |
| Phi-4 | 1.0% | Independent | Epoch AI | 28 Aug 2026 |
| Qwen3-30B-A3B Alibaba Group · None effort | 1.0% | Independent | Epoch AI | 30 Aug 2026 |
| Qwen3-32B Alibaba Group · None effort | 1.0% | Independent | Epoch AI | 28 Aug 2026 |
| Qwen3-4B Alibaba Group · None effort | 1.0% | Independent | Epoch AI | 28 Aug 2026 |
| Qwen3.5-35B-A3B | 1.0% | Independent | Epoch AI | 28 Aug 2026 |
| GPT-5.6 Luna OpenAI · None effort | 2.0% | Independent | Epoch AI | 7 Aug 2026 |
| gpt-oss-20b OpenAI · Low effort | 2.0% | Independent | Epoch AI | 27 Aug 2026 |
| Qwen3-30B-A3B-Instruct-2507 | 2.0% | Independent | Epoch AI | 30 Aug 2026 |
| Qwen3.5-9B | 2.0% | Independent | Epoch AI | 27 Aug 2026 |
| Claude Sonnet 4.6 Anthropic · Max effort | 3.0% | Independent | Epoch AI | 6 Aug 2026 |
| DeepSeek-R1-0528-Qwen3-8B | 3.0% | Independent | Epoch AI | 28 Aug 2026 |
| GPT-5.4 mini OpenAI · None effort | 3.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5.4 nano OpenAI · None effort | 3.0% | Independent | Epoch AI | 7 Aug 2026 |
| Magistral Small 1.2 | 3.0% | Independent | Epoch AI | 30 Aug 2026 |
| Claude Opus 4.5 | 4.0% | Independent | Epoch AI | 6 Aug 2026 |
| Claude Sonnet 4.5 | 4.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-4 | 4.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5.2 OpenAI · None effort | 4.0% | Independent | Epoch AI | 13 Jul 2026 |
| gpt-oss-20b OpenAI · Medium effort | 4.0% | Independent | Epoch AI | 27 Aug 2026 |
| MiniMax-M3 MiniMax · None effort | 4.0% | Independent | Epoch AI | 10 Aug 2026 |
| Qwen3-14B | 4.0% | Independent | Epoch AI | 30 Aug 2026 |
| Qwen3-30B-A3B | 4.0% | Independent | Epoch AI | 30 Aug 2026 |
| Qwen3-4B-Instruct-2507 | 4.0% | Independent | Epoch AI | 28 Aug 2026 |
| Qwen3-Max | 4.0% | Independent | Epoch AI | 10 Dec 2025 |
| Qwen3.6-35B-A3B Alibaba Group · None effort | 4.0% | Independent | Epoch AI | 7 Aug 2026 |
| Claude 3 Opus | 5.0% | Independent | Epoch AI | 15 Jul 2026 |
| Claude Sonnet 4.6 Anthropic · High effort | 5.0% | Independent | Epoch AI | 13 Jul 2026 |
| Gemma 4 31B Google DeepMind · Minimal effort | 5.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-5.4 OpenAI · None effort | 5.0% | Independent | Epoch AI | 15 Jul 2026 |
| GPT-5.6 Terra OpenAI · None effort | 5.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3-32B | 5.0% | Independent | Epoch AI | 28 Aug 2026 |
| Qwen3-8B | 5.0% | Independent | Epoch AI | 27 Aug 2026 |
| QwQ-32B | 5.0% | Independent | Epoch AI | 28 Aug 2026 |
| Gemma 4 26B A4B Google DeepMind · Minimal effort | 6.0% | Independent | Epoch AI | 6 Aug 2026 |
| GLM-4.7 | 6.0% | Independent | Epoch AI | 29 Jan 2026 |
| GLM-5.2 Z.ai (Zhipu AI) · None effort | 6.0% | Independent | Epoch AI | 10 Aug 2026 |
| GPT-4 Turbo | 6.0% | Independent | Epoch AI | 15 Jul 2026 |
| GPT-4.1 | 6.0% | Independent | Epoch AI | 7 Aug 2026 |
| o3-mini OpenAI · Low effort | 6.0% | Independent | Epoch AI | 15 Jul 2026 |
| Claude Opus 4.1 | 7.0% | Independent | Epoch AI | 20 Jul 2026 |
| Claude Opus 4.7 Anthropic · Max effort | 7.0% | Independent | Epoch AI | 6 Aug 2026 |
| DeepSeek-V4-Pro DeepSeek · None effort | 7.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-4.1 mini | 7.0% | Independent | Epoch AI | 15 Jul 2026 |
| GPT-5 mini OpenAI · Minimal effort | 7.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5.6 Sol OpenAI · None effort | 7.0% | Independent | Epoch AI | 7 Aug 2026 |
| o1 OpenAI · Low effort | 7.0% | Independent | Epoch AI | 15 Jul 2026 |
| Claude Haiku 4.5 Anthropic · 32K effort | 8.0% | Independent | Epoch AI | 16 Jul 2026 |
| Claude Sonnet 4.6 Anthropic · Medium effort | 8.0% | Independent | Epoch AI | 13 Jul 2026 |
| Qwen3-30B-A3B-Thinking-2507 | 8.0% | Independent | Epoch AI | 30 Aug 2026 |
| o3-mini OpenAI · Medium effort | 9.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.6-27B Alibaba Group · None effort | 9.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.7-Flash Alibaba Group · None effort | 9.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.7-Plus Alibaba Group · None effort | 9.0% | Independent | Epoch AI | 7 Aug 2026 |
| Claude Opus 4.6 Anthropic · 64K effort | 10.0% | Independent | Epoch AI | 6 Feb 2026 |
| GLM-5 | 10.0% | Independent | Epoch AI | 12 Feb 2026 |
| GPT-5.5 OpenAI · None effort | 10.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.5-35B-A3B Alibaba Group · None effort | 10.0% | Independent | Epoch AI | 30 Aug 2026 |
| Claude Opus 4.5 Anthropic · 32K effort | 12.0% | Independent | Epoch AI | 8 Dec 2025 |
| Claude Sonnet 4.5 Anthropic · 32K effort | 12.0% | Independent | Epoch AI | 8 Dec 2025 |
| GPT-5 mini OpenAI · Low effort | 12.0% | Independent | Epoch AI | 7 Aug 2026 |
| o1 OpenAI · Medium effort | 12.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3-235B-A22B-Thinking-2507 | 12.0% | Independent | Epoch AI | 11 Dec 2025 |
| Qwen3.5-397B-A17B | 12.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.5-9B Alibaba Group · None effort | 12.0% | Independent | Epoch AI | 27 Aug 2026 |
| Claude Opus 4.6 Anthropic · 120K effort | 13.0% | Independent | Epoch AI | 20 Feb 2026 |
| Claude Opus 4.8 Anthropic · None effort | 13.0% | Independent | Epoch AI | 6 Aug 2026 |
| Claude Sonnet 4.6 Anthropic · 32K effort | 13.0% | Independent | Epoch AI | 20 Feb 2026 |
| DeepSeek-V4-Pro DeepSeek · High effort | 13.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-4o | 13.0% | Independent | Epoch AI | 15 Jul 2026 |
| Qwen3.5-397B-A17B Alibaba Group · None effort | 13.0% | Independent | Epoch AI | 7 Aug 2026 |
| Seed-OSS-36B-Instruct | 13.0% | Independent | Epoch AI | 28 Aug 2026 |
| Claude Opus 4.6 Anthropic · Max effort | 14.0% | Independent | Epoch AI | 6 Aug 2026 |
| DeepSeek-V3.2 | 14.0% | Independent | Epoch AI | 16 Dec 2025 |
| GLM-5.2 Z.ai (Zhipu AI) · Low effort | 14.0% | Independent | Epoch AI | 10 Aug 2026 |
| GLM-5.3-Flash Z.ai (Zhipu AI) · Max effort | 14.0% | Independent | Epoch AI | 26 Aug 2026 |
| GPT-5.1 OpenAI · Low effort | 14.0% | Independent | Epoch AI | 7 Aug 2026 |
| MiniMax-M3 | 14.0% | Independent | Epoch AI | 10 Aug 2026 |
| o4-mini OpenAI · Low effort | 14.0% | Independent | Epoch AI | 11 Jul 2026 |
| GPT-5 nano OpenAI · Low effort | 15.0% | Independent | Epoch AI | 13 Jul 2026 |
| o1 OpenAI · High effort | 15.0% | Independent | Epoch AI | 7 Aug 2026 |
| Claude Sonnet 5 Anthropic · Max effort | 16.0% | Independent | Epoch AI | 30 Jun 2026 |
| GPT-5 OpenAI · Minimal effort | 16.0% | Independent | Epoch AI | 15 Jul 2026 |
| Claude Opus 4.6 Anthropic · 32K effort | 17.0% | Independent | Epoch AI | 6 Feb 2026 |
| GPT-5.1 OpenAI · None effort | 17.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5.4 nano OpenAI · Low effort | 17.0% | Independent | Epoch AI | 7 Aug 2026 |
| o3-mini OpenAI · High effort | 17.0% | Independent | Epoch AI | 8 Dec 2025 |
| Qwen3.6-Plus | 17.0% | Independent | Epoch AI | 7 Aug 2026 |
| Gemini 3.5 Flash-Lite Google DeepMind · Low effort | 18.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-5.4 mini OpenAI · High effort | 18.0% | Independent | Epoch AI | 15 Apr 2026 |
| Inkling Small Thinking Machines Lab · Xhigh effort | 18.0% | Independent | Epoch AI | 14 Aug 2026 |
| GLM-5.1 | 19.0% | Independent | Epoch AI | 10 Aug 2026 |
| Qwen3.7-Max | 19.0% | Independent | Epoch AI | 7 Aug 2026 |
| Claude Opus 4.7 Anthropic · Low effort | 20.0% | Independent | Epoch AI | 14 Jul 2026 |
| Claude Opus 5 Anthropic · Low effort | 20.0% | Independent | Epoch AI | 6 Aug 2026 |
| DeepSeek-V4-Pro DeepSeek · Max effort | 20.0% | Independent | Epoch AI | 16 Jun 2026 |
| Gemini 2.5 Pro | 20.0% | Independent | Epoch AI | 8 Dec 2025 |
| Gemini 3.1 Flash-Lite Google DeepMind · High effort | 20.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-5.4 OpenAI · Low effort | 20.0% | Independent | Epoch AI | 15 Jul 2026 |
| gpt-oss-120b OpenAI · High effort | 20.0% | Independent | Epoch AI | 11 Dec 2025 |
| Kimi K2 Thinking | 20.0% | Independent | Epoch AI | 10 Dec 2025 |
| Kimi K3 Moonshot AI · Low effort | 20.0% | Independent | Epoch AI | 7 Aug 2026 |
| o4-mini OpenAI · Medium effort | 20.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.6-Flash | 20.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.6-Max-Preview | 20.0% | Independent | Epoch AI | 7 Aug 2026 |
| Gemini 3.5 Flash-Lite Google DeepMind · Minimal effort | 21.0% | Independent | Epoch AI | 6 Aug 2026 |
| GLM-5.2 Z.ai (Zhipu AI) · Max effort | 21.0% | Independent | Epoch AI | 17 Jun 2026 |
| GLM-5.3 Z.ai (Zhipu AI) · Max effort | 21.0% | Independent | Epoch AI | 24 Aug 2026 |
| GPT-5.6 Luna OpenAI · Low effort | 21.0% | Independent | Epoch AI | 7 Aug 2026 |
| Inkling Thinking Machines Lab · Xhigh effort | 21.0% | Independent | Epoch AI | 5 Aug 2026 |
| Kimi K2.7 Code | 21.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.5-Flash | 21.0% | Independent | Epoch AI | 7 Aug 2026 |
| Gemini 3.5 Flash-Lite Google DeepMind · High effort | 22.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-5.6 Terra OpenAI · Low effort | 22.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.5-Plus | 22.0% | Independent | Epoch AI | 7 Aug 2026 |
| Qwen3.6-27B | 22.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5.2 OpenAI · Low effort | 23.0% | Independent | Epoch AI | 11 Dec 2025 |
| Qwen3.7-Flash | 23.0% | Independent | Epoch AI | 7 Aug 2026 |
| Gemini 3.1 Flash-Lite Google DeepMind · Minimal effort | 24.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-5 OpenAI · Low effort | 24.0% | Independent | Epoch AI | 15 Jul 2026 |
| GPT-5.4 mini OpenAI · Xhigh effort | 24.0% | Independent | Epoch AI | 7 Aug 2026 |
| Grok 4.20 | 24.0% | Independent | Epoch AI | 13 Jul 2026 |
| Qwen3.7-Plus | 24.0% | Independent | Epoch AI | 7 Aug 2026 |
| Gemini 3.1 Flash-Lite Google DeepMind · Low effort | 25.0% | Independent | Epoch AI | 6 Aug 2026 |
| Grok 4.3 SpaceXAI (xAI) · High effort | 25.0% | Independent | Epoch AI | 17 Jun 2026 |
| Kimi K3 Moonshot AI · High effort | 25.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5.5 OpenAI · Low effort | 26.0% | Independent | Epoch AI | 7 Aug 2026 |
| Kimi K2.6 | 26.0% | Independent | Epoch AI | 7 May 2026 |
| o4-mini OpenAI · High effort | 26.0% | Independent | Epoch AI | 8 Dec 2025 |
| Qwen3.6-35B-A3B | 26.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5 nano OpenAI · High effort | 27.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5.6 Sol OpenAI · Low effort | 27.0% | Independent | Epoch AI | 7 Aug 2026 |
| o3 OpenAI · Low effort | 27.0% | Independent | Epoch AI | 15 Jul 2026 |
| Claude Fable 5 Anthropic · Low effort | 28.0% | Independent | Epoch AI | 6 Aug 2026 |
| Grok 4 | 28.0% | Independent | Epoch AI | 30 Jan 2026 |
| Claude Opus 4.8 Anthropic · Low effort | 29.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-5 OpenAI · Medium effort | 29.0% | Independent | Epoch AI | 15 Jul 2026 |
| Qwen3.8-Max Alibaba Group · Xhigh effort | 29.0% | Independent | Epoch AI | 4 Aug 2026 |
| Claude Opus 4.7 Anthropic · Xhigh effort | 30.0% | Independent | Epoch AI | 20 Apr 2026 |
| GPT-5 mini OpenAI · High effort | 30.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5.4 nano OpenAI · High effort | 30.0% | Independent | Epoch AI | 14 Apr 2026 |
| Gemini 3 Pro | 31.0% | Independent | Epoch AI | 8 Dec 2025 |
| Grok 4.6 SpaceXAI (xAI) · Xhigh effort | 31.0% | Independent | Epoch AI | 14 Aug 2026 |
| GPT-5.1 OpenAI · High effort | 32.0% | Independent | Epoch AI | 8 Dec 2025 |
| Claude Opus 5 | 33.0% | Independent | Epoch AI | 6 Aug 2026 |
| DeepSeek-V4-Flash DeepSeek · Max effort | 33.0% | Independent | Epoch AI | 2 Aug 2026 |
| Claude Opus 4.8 Anthropic · Max effort | 34.0% | Independent | Epoch AI | 29 May 2026 |
| o3 OpenAI · High effort | 34.0% | Independent | Epoch AI | 7 Aug 2026 |
| Claude Sonnet 5 Anthropic · Xhigh effort | 35.0% | Independent | Epoch AI | 30 Jun 2026 |
| Gemini 3.6 Flash Google DeepMind · Minimal effort | 35.0% | Independent | Epoch AI | 7 Aug 2026 |
| Muse Spark 1.3 Meta · Xhigh effort | 35.0% | Independent | Epoch AI | 16 Sep 2026 |
| Grok 4.5 SpaceXAI (xAI) · High effort | 36.0% | Independent | Epoch AI | 8 Jul 2026 |
| GPT-5 OpenAI · High effort | 37.0% | Independent | Epoch AI | 8 Dec 2025 |
| Gemini 3 Flash | 38.0% | Independent | Epoch AI | 17 Dec 2025 |
| GPT-5.4 OpenAI · Medium effort | 38.0% | Independent | Epoch AI | 15 Jul 2026 |
| GPT-5.4 OpenAI · High effort | 38.0% | Independent | Epoch AI | 15 Jul 2026 |
| Muse Spark 1.3 Meta · Max effort | 38.0% | Independent | Epoch AI | 18 Sep 2026 |
| o3 OpenAI · Medium effort | 38.0% | Independent | Epoch AI | 7 Aug 2026 |
| Kimi K3 Moonshot AI · Max effort | 39.0% | Independent | Epoch AI | 16 Jul 2026 |
| Gemini 3 Flash Google DeepMind · High effort | 40.0% | Independent | Epoch AI | 6 Aug 2026 |
| Gemini 3.6 Flash Google DeepMind · High effort | 40.0% | Independent | Epoch AI | 2 Aug 2026 |
| GPT-5.2 OpenAI · Medium effort | 40.0% | Independent | Epoch AI | 11 Dec 2025 |
| GPT-5.2 OpenAI · High effort | 40.0% | Independent | Epoch AI | 11 Dec 2025 |
| GPT-5.6 Luna OpenAI · Max effort | 40.0% | Independent | Epoch AI | 9 Jul 2026 |
| Grok 4.6 SpaceXAI (xAI) · High effort | 40.0% | Independent | Epoch AI | 12 Aug 2026 |
| Qwen3.8-Max Alibaba Group · Xhigh effort | 40.0% | Independent | Epoch AI | 2 Sep 2026 |
| Claude Fable 5 Anthropic · High effort | 41.0% | Independent | Epoch AI | 6 Aug 2026 |
| Claude Fable 5 Anthropic · Max effort | 41.0% | Independent | Epoch AI | 9 Jun 2026 |
| Claude Opus 5 Anthropic · Max effort | 42.0% | Independent | Epoch AI | 24 Jul 2026 |
| Gemini 3.5 Flash Google DeepMind · Minimal effort | 43.0% | Independent | Epoch AI | 15 Jul 2026 |
| Gemini 3.6 Flash Google DeepMind · Low effort | 43.0% | Independent | Epoch AI | 7 Aug 2026 |
| GPT-5.4 OpenAI · Xhigh effort | 44.0% | Independent | Epoch AI | 11 Mar 2026 |
| Gemini 3.5 Flash Google DeepMind · Low effort | 45.0% | Independent | Epoch AI | 6 Aug 2026 |
| Claude Fable 5.1 Anthropic · Max effort | 47.0% | Independent | Epoch AI | 1 Sep 2026 |
| DeepSeek-V4-Pro DeepSeek · Max effort | 47.0% | Independent | Epoch AI | 18 Aug 2026 |
| Gemini 3.7 Flash Google DeepMind · High effort | 47.0% | Independent | Epoch AI | 14 Aug 2026 |
| Gemini 3.1 Pro Google DeepMind · High effort | 49.0% | Independent | Epoch AI | 6 Aug 2026 |
| GPT-5.2 OpenAI · Xhigh effort | 49.0% | Independent | Epoch AI | 15 Dec 2025 |
| Gemini 3.5 Flash Google DeepMind · High effort | 50.0% | Independent | Epoch AI | 28 May 2026 |
| GPT-5.6 Terra OpenAI · Max effort | 54.0% | Independent | Epoch AI | 9 Jul 2026 |
| Gemini 3.1 Pro | 55.0% | Independent | Epoch AI | 19 Feb 2026 |
| GPT-5.6 Sol OpenAI · Max effort | 55.0% | Independent | Epoch AI | 9 Jul 2026 |
| GPT-5.4 Pro OpenAI · Xhigh effort | 58.6% | Independent | Epoch AI | 19 Mar 2026 |
| Gemini 3.8 Flash Google DeepMind · High effort | 61.0% | Independent | Epoch AI | 2 Sep 2026 |
| GPT-5.6 Sol OpenAI · Promax effort | 64.0% | Independent | Epoch AI | 10 Jul 2026 |
| GPT-6 Astra OpenAI · Max effort | 72.0% | Independent | Epoch AI | 30 Aug 2026 |
- Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks, CC BY 4.0.