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

Official leaderboard

Every result we hold, whoever ran it. Only independent and third-party rows count towards a score.

Leaderboard
ModelPuzzles solvedProvenanceSourceEvaluated
GPT-6 Astra
OpenAI · Max effort
72.0%IndependentEpoch AI30 Aug 2026
GPT-5.6 Sol
OpenAI · Promax effort
64.0%IndependentEpoch AI10 Jul 2026
Gemini 3.8 Flash
Google DeepMind · High effort
61.0%IndependentEpoch AI2 Sep 2026
GPT-5.4 Pro
OpenAI · Xhigh effort
58.6%IndependentEpoch AI19 Mar 2026
Gemini 3.1 Pro55.0%IndependentEpoch AI19 Feb 2026
GPT-5.6 Sol
OpenAI · Max effort
55.0%IndependentEpoch AI9 Jul 2026
GPT-5.6 Terra
OpenAI · Max effort
54.0%IndependentEpoch AI9 Jul 2026
Gemini 3.5 Flash
Google DeepMind · High effort
50.0%IndependentEpoch AI28 May 2026
Gemini 3.1 Pro
Google DeepMind · High effort
49.0%IndependentEpoch AI6 Aug 2026
GPT-5.2
OpenAI · Xhigh effort
49.0%IndependentEpoch AI15 Dec 2025
Claude Fable 5.1
Anthropic · Max effort
47.0%IndependentEpoch AI1 Sep 2026
DeepSeek-V4-Pro
DeepSeek · Max effort
47.0%IndependentEpoch AI18 Aug 2026
Gemini 3.7 Flash
Google DeepMind · High effort
47.0%IndependentEpoch AI14 Aug 2026
Gemini 3.5 Flash
Google DeepMind · Low effort
45.0%IndependentEpoch AI6 Aug 2026
GPT-5.4
OpenAI · Xhigh effort
44.0%IndependentEpoch AI11 Mar 2026
Gemini 3.5 Flash
Google DeepMind · Minimal effort
43.0%IndependentEpoch AI15 Jul 2026
Gemini 3.6 Flash
Google DeepMind · Low effort
43.0%IndependentEpoch AI7 Aug 2026
Claude Opus 5
Anthropic · Max effort
42.0%IndependentEpoch AI24 Jul 2026
Claude Fable 5
Anthropic · High effort
41.0%IndependentEpoch AI6 Aug 2026
Claude Fable 5
Anthropic · Max effort
41.0%IndependentEpoch AI9 Jun 2026
Gemini 3 Flash
Google DeepMind · High effort
40.0%IndependentEpoch AI6 Aug 2026
Gemini 3.6 Flash
Google DeepMind · High effort
40.0%IndependentEpoch AI2 Aug 2026
GPT-5.2
OpenAI · Medium effort
40.0%IndependentEpoch AI11 Dec 2025
GPT-5.2
OpenAI · High effort
40.0%IndependentEpoch AI11 Dec 2025
GPT-5.6 Luna
OpenAI · Max effort
40.0%IndependentEpoch AI9 Jul 2026
Grok 4.6
SpaceXAI (xAI) · High effort
40.0%IndependentEpoch AI12 Aug 2026
Qwen3.8-Max
Alibaba Group · Xhigh effort
40.0%IndependentEpoch AI2 Sep 2026
Kimi K3
Moonshot AI · Max effort
39.0%IndependentEpoch AI16 Jul 2026
Gemini 3 Flash38.0%IndependentEpoch AI17 Dec 2025
GPT-5.4
OpenAI · Medium effort
38.0%IndependentEpoch AI15 Jul 2026
GPT-5.4
OpenAI · High effort
38.0%IndependentEpoch AI15 Jul 2026
Muse Spark 1.3
Meta · Max effort
38.0%IndependentEpoch AI18 Sep 2026
o3
OpenAI · Medium effort
38.0%IndependentEpoch AI7 Aug 2026
GPT-5
OpenAI · High effort
37.0%IndependentEpoch AI8 Dec 2025
Grok 4.5
SpaceXAI (xAI) · High effort
36.0%IndependentEpoch AI8 Jul 2026
Claude Sonnet 5
Anthropic · Xhigh effort
35.0%IndependentEpoch AI30 Jun 2026
Gemini 3.6 Flash
Google DeepMind · Minimal effort
35.0%IndependentEpoch AI7 Aug 2026
Muse Spark 1.3
Meta · Xhigh effort
35.0%IndependentEpoch AI16 Sep 2026
Claude Opus 4.8
Anthropic · Max effort
34.0%IndependentEpoch AI29 May 2026
o3
OpenAI · High effort
34.0%IndependentEpoch AI7 Aug 2026
Claude Opus 533.0%IndependentEpoch AI6 Aug 2026
DeepSeek-V4-Flash
DeepSeek · Max effort
33.0%IndependentEpoch AI2 Aug 2026
GPT-5.1
OpenAI · High effort
32.0%IndependentEpoch AI8 Dec 2025
Gemini 3 Pro31.0%IndependentEpoch AI8 Dec 2025
Grok 4.6
SpaceXAI (xAI) · Xhigh effort
31.0%IndependentEpoch AI14 Aug 2026
Claude Opus 4.7
Anthropic · Xhigh effort
30.0%IndependentEpoch AI20 Apr 2026
GPT-5 mini
OpenAI · High effort
30.0%IndependentEpoch AI7 Aug 2026
GPT-5.4 nano
OpenAI · High effort
30.0%IndependentEpoch AI14 Apr 2026
Claude Opus 4.8
Anthropic · Low effort
29.0%IndependentEpoch AI6 Aug 2026
GPT-5
OpenAI · Medium effort
29.0%IndependentEpoch AI15 Jul 2026
Qwen3.8-Max
Alibaba Group · Xhigh effort
29.0%IndependentEpoch AI4 Aug 2026
Claude Fable 5
Anthropic · Low effort
28.0%IndependentEpoch AI6 Aug 2026
Grok 428.0%IndependentEpoch AI30 Jan 2026
GPT-5 nano
OpenAI · High effort
27.0%IndependentEpoch AI7 Aug 2026
GPT-5.6 Sol
OpenAI · Low effort
27.0%IndependentEpoch AI7 Aug 2026
o3
OpenAI · Low effort
27.0%IndependentEpoch AI15 Jul 2026
GPT-5.5
OpenAI · Low effort
26.0%IndependentEpoch AI7 Aug 2026
Kimi K2.626.0%IndependentEpoch AI7 May 2026
o4-mini
OpenAI · High effort
26.0%IndependentEpoch AI8 Dec 2025
Qwen3.6-35B-A3B26.0%IndependentEpoch AI7 Aug 2026
Gemini 3.1 Flash-Lite
Google DeepMind · Low effort
25.0%IndependentEpoch AI6 Aug 2026
Grok 4.3
SpaceXAI (xAI) · High effort
25.0%IndependentEpoch AI17 Jun 2026
Kimi K3
Moonshot AI · High effort
25.0%IndependentEpoch AI7 Aug 2026
Gemini 3.1 Flash-Lite
Google DeepMind · Minimal effort
24.0%IndependentEpoch AI6 Aug 2026
GPT-5
OpenAI · Low effort
24.0%IndependentEpoch AI15 Jul 2026
GPT-5.4 mini
OpenAI · Xhigh effort
24.0%IndependentEpoch AI7 Aug 2026
Grok 4.2024.0%IndependentEpoch AI13 Jul 2026
Qwen3.7-Plus24.0%IndependentEpoch AI7 Aug 2026
GPT-5.2
OpenAI · Low effort
23.0%IndependentEpoch AI11 Dec 2025
Qwen3.7-Flash23.0%IndependentEpoch AI7 Aug 2026
Gemini 3.5 Flash-Lite
Google DeepMind · High effort
22.0%IndependentEpoch AI6 Aug 2026
GPT-5.6 Terra
OpenAI · Low effort
22.0%IndependentEpoch AI7 Aug 2026
Qwen3.5-Plus22.0%IndependentEpoch AI7 Aug 2026
Qwen3.6-27B22.0%IndependentEpoch AI7 Aug 2026
Gemini 3.5 Flash-Lite
Google DeepMind · Minimal effort
21.0%IndependentEpoch AI6 Aug 2026
GLM-5.2
Z.ai (Zhipu AI) · Max effort
21.0%IndependentEpoch AI17 Jun 2026
GLM-5.3
Z.ai (Zhipu AI) · Max effort
21.0%IndependentEpoch AI24 Aug 2026
GPT-5.6 Luna
OpenAI · Low effort
21.0%IndependentEpoch AI7 Aug 2026
Inkling
Thinking Machines Lab · Xhigh effort
21.0%IndependentEpoch AI5 Aug 2026
Kimi K2.7 Code21.0%IndependentEpoch AI7 Aug 2026
Qwen3.5-Flash21.0%IndependentEpoch AI7 Aug 2026
Claude Opus 4.7
Anthropic · Low effort
20.0%IndependentEpoch AI14 Jul 2026
Claude Opus 5
Anthropic · Low effort
20.0%IndependentEpoch AI6 Aug 2026
DeepSeek-V4-Pro
DeepSeek · Max effort
20.0%IndependentEpoch AI16 Jun 2026
Gemini 2.5 Pro20.0%IndependentEpoch AI8 Dec 2025
Gemini 3.1 Flash-Lite
Google DeepMind · High effort
20.0%IndependentEpoch AI6 Aug 2026
GPT-5.4
OpenAI · Low effort
20.0%IndependentEpoch AI15 Jul 2026
gpt-oss-120b
OpenAI · High effort
20.0%IndependentEpoch AI11 Dec 2025
Kimi K2 Thinking20.0%IndependentEpoch AI10 Dec 2025
Kimi K3
Moonshot AI · Low effort
20.0%IndependentEpoch AI7 Aug 2026
o4-mini
OpenAI · Medium effort
20.0%IndependentEpoch AI7 Aug 2026
Qwen3.6-Flash20.0%IndependentEpoch AI7 Aug 2026
Qwen3.6-Max-Preview20.0%IndependentEpoch AI7 Aug 2026
GLM-5.119.0%IndependentEpoch AI10 Aug 2026
Qwen3.7-Max19.0%IndependentEpoch AI7 Aug 2026
Gemini 3.5 Flash-Lite
Google DeepMind · Low effort
18.0%IndependentEpoch AI6 Aug 2026
GPT-5.4 mini
OpenAI · High effort
18.0%IndependentEpoch AI15 Apr 2026
Inkling Small
Thinking Machines Lab · Xhigh effort
18.0%IndependentEpoch AI14 Aug 2026
Claude Opus 4.6
Anthropic · 32K effort
17.0%IndependentEpoch AI6 Feb 2026
GPT-5.1
OpenAI · None effort
17.0%IndependentEpoch AI7 Aug 2026
GPT-5.4 nano
OpenAI · Low effort
17.0%IndependentEpoch AI7 Aug 2026
o3-mini
OpenAI · High effort
17.0%IndependentEpoch AI8 Dec 2025
Qwen3.6-Plus17.0%IndependentEpoch AI7 Aug 2026
Claude Sonnet 5
Anthropic · Max effort
16.0%IndependentEpoch AI30 Jun 2026
GPT-5
OpenAI · Minimal effort
16.0%IndependentEpoch AI15 Jul 2026
GPT-5 nano
OpenAI · Low effort
15.0%IndependentEpoch AI13 Jul 2026
o1
OpenAI · High effort
15.0%IndependentEpoch AI7 Aug 2026
Claude Opus 4.6
Anthropic · Max effort
14.0%IndependentEpoch AI6 Aug 2026
DeepSeek-V3.214.0%IndependentEpoch AI16 Dec 2025
GLM-5.2
Z.ai (Zhipu AI) · Low effort
14.0%IndependentEpoch AI10 Aug 2026
GLM-5.3-Flash
Z.ai (Zhipu AI) · Max effort
14.0%IndependentEpoch AI26 Aug 2026
GPT-5.1
OpenAI · Low effort
14.0%IndependentEpoch AI7 Aug 2026
MiniMax-M314.0%IndependentEpoch AI10 Aug 2026
o4-mini
OpenAI · Low effort
14.0%IndependentEpoch AI11 Jul 2026
Claude Opus 4.6
Anthropic · 120K effort
13.0%IndependentEpoch AI20 Feb 2026
Claude Opus 4.8
Anthropic · None effort
13.0%IndependentEpoch AI6 Aug 2026
Claude Sonnet 4.6
Anthropic · 32K effort
13.0%IndependentEpoch AI20 Feb 2026
DeepSeek-V4-Pro
DeepSeek · High effort
13.0%IndependentEpoch AI6 Aug 2026
GPT-4o13.0%IndependentEpoch AI15 Jul 2026
Qwen3.5-397B-A17B
Alibaba Group · None effort
13.0%IndependentEpoch AI7 Aug 2026
Seed-OSS-36B-Instruct13.0%IndependentEpoch AI28 Aug 2026
Claude Opus 4.5
Anthropic · 32K effort
12.0%IndependentEpoch AI8 Dec 2025
Claude Sonnet 4.5
Anthropic · 32K effort
12.0%IndependentEpoch AI8 Dec 2025
GPT-5 mini
OpenAI · Low effort
12.0%IndependentEpoch AI7 Aug 2026
o1
OpenAI · Medium effort
12.0%IndependentEpoch AI7 Aug 2026
Qwen3-235B-A22B-Thinking-250712.0%IndependentEpoch AI11 Dec 2025
Qwen3.5-397B-A17B12.0%IndependentEpoch AI7 Aug 2026
Qwen3.5-9B
Alibaba Group · None effort
12.0%IndependentEpoch AI27 Aug 2026
Claude Opus 4.6
Anthropic · 64K effort
10.0%IndependentEpoch AI6 Feb 2026
GLM-510.0%IndependentEpoch AI12 Feb 2026
GPT-5.5
OpenAI · None effort
10.0%IndependentEpoch AI7 Aug 2026
Qwen3.5-35B-A3B
Alibaba Group · None effort
10.0%IndependentEpoch AI30 Aug 2026
o3-mini
OpenAI · Medium effort
9.0%IndependentEpoch AI7 Aug 2026
Qwen3.6-27B
Alibaba Group · None effort
9.0%IndependentEpoch AI7 Aug 2026
Qwen3.7-Flash
Alibaba Group · None effort
9.0%IndependentEpoch AI7 Aug 2026
Qwen3.7-Plus
Alibaba Group · None effort
9.0%IndependentEpoch AI7 Aug 2026
Claude Haiku 4.5
Anthropic · 32K effort
8.0%IndependentEpoch AI16 Jul 2026
Claude Sonnet 4.6
Anthropic · Medium effort
8.0%IndependentEpoch AI13 Jul 2026
Qwen3-30B-A3B-Thinking-25078.0%IndependentEpoch AI30 Aug 2026
Claude Opus 4.17.0%IndependentEpoch AI20 Jul 2026
Claude Opus 4.7
Anthropic · Max effort
7.0%IndependentEpoch AI6 Aug 2026
DeepSeek-V4-Pro
DeepSeek · None effort
7.0%IndependentEpoch AI6 Aug 2026
GPT-4.1 mini7.0%IndependentEpoch AI15 Jul 2026
GPT-5 mini
OpenAI · Minimal effort
7.0%IndependentEpoch AI7 Aug 2026
GPT-5.6 Sol
OpenAI · None effort
7.0%IndependentEpoch AI7 Aug 2026
o1
OpenAI · Low effort
7.0%IndependentEpoch AI15 Jul 2026
Gemma 4 26B A4B
Google DeepMind · Minimal effort
6.0%IndependentEpoch AI6 Aug 2026
GLM-4.76.0%IndependentEpoch AI29 Jan 2026
GLM-5.2
Z.ai (Zhipu AI) · None effort
6.0%IndependentEpoch AI10 Aug 2026
GPT-4 Turbo6.0%IndependentEpoch AI15 Jul 2026
GPT-4.16.0%IndependentEpoch AI7 Aug 2026
o3-mini
OpenAI · Low effort
6.0%IndependentEpoch AI15 Jul 2026
Claude 3 Opus5.0%IndependentEpoch AI15 Jul 2026
Claude Sonnet 4.6
Anthropic · High effort
5.0%IndependentEpoch AI13 Jul 2026
Gemma 4 31B
Google DeepMind · Minimal effort
5.0%IndependentEpoch AI6 Aug 2026
GPT-5.4
OpenAI · None effort
5.0%IndependentEpoch AI15 Jul 2026
GPT-5.6 Terra
OpenAI · None effort
5.0%IndependentEpoch AI7 Aug 2026
Qwen3-32B5.0%IndependentEpoch AI28 Aug 2026
Qwen3-8B5.0%IndependentEpoch AI27 Aug 2026
QwQ-32B5.0%IndependentEpoch AI28 Aug 2026
Claude Opus 4.54.0%IndependentEpoch AI6 Aug 2026
Claude Sonnet 4.54.0%IndependentEpoch AI6 Aug 2026
GPT-44.0%IndependentEpoch AI7 Aug 2026
GPT-5.2
OpenAI · None effort
4.0%IndependentEpoch AI13 Jul 2026
gpt-oss-20b
OpenAI · Medium effort
4.0%IndependentEpoch AI27 Aug 2026
MiniMax-M3
MiniMax · None effort
4.0%IndependentEpoch AI10 Aug 2026
Qwen3-14B4.0%IndependentEpoch AI30 Aug 2026
Qwen3-30B-A3B4.0%IndependentEpoch AI30 Aug 2026
Qwen3-4B-Instruct-25074.0%IndependentEpoch AI28 Aug 2026
Qwen3-Max4.0%IndependentEpoch AI10 Dec 2025
Qwen3.6-35B-A3B
Alibaba Group · None effort
4.0%IndependentEpoch AI7 Aug 2026
Claude Sonnet 4.6
Anthropic · Max effort
3.0%IndependentEpoch AI6 Aug 2026
DeepSeek-R1-0528-Qwen3-8B3.0%IndependentEpoch AI28 Aug 2026
GPT-5.4 mini
OpenAI · None effort
3.0%IndependentEpoch AI7 Aug 2026
GPT-5.4 nano
OpenAI · None effort
3.0%IndependentEpoch AI7 Aug 2026
Magistral Small 1.23.0%IndependentEpoch AI30 Aug 2026
GPT-5.6 Luna
OpenAI · None effort
2.0%IndependentEpoch AI7 Aug 2026
gpt-oss-20b
OpenAI · Low effort
2.0%IndependentEpoch AI27 Aug 2026
Qwen3-30B-A3B-Instruct-25072.0%IndependentEpoch AI30 Aug 2026
Qwen3.5-9B2.0%IndependentEpoch AI27 Aug 2026
DeepSeek-R1-Distill-Qwen-14B1.0%IndependentEpoch AI28 Aug 2026
DeepSeek-R1-Distill-Qwen-32B1.0%IndependentEpoch AI28 Aug 2026
DeepSeek-V3.21.0%IndependentEpoch AI16 Jul 2026
GPT-5 nano
OpenAI · Minimal effort
1.0%IndependentEpoch AI13 Jul 2026
Phi-41.0%IndependentEpoch AI28 Aug 2026
Qwen3-30B-A3B
Alibaba Group · None effort
1.0%IndependentEpoch AI30 Aug 2026
Qwen3-32B
Alibaba Group · None effort
1.0%IndependentEpoch AI28 Aug 2026
Qwen3-4B
Alibaba Group · None effort
1.0%IndependentEpoch AI28 Aug 2026
Qwen3.5-35B-A3B1.0%IndependentEpoch AI28 Aug 2026
DeepSeek LLM 67B Chat0.0%IndependentEpoch AI28 Aug 2026
DeepSeek-R1-Distill-Qwen-1.5B0.0%IndependentEpoch AI28 Aug 2026
Gemma 3 12B0.0%IndependentEpoch AI28 Aug 2026
Gemma 3 1B0.0%IndependentEpoch AI28 Aug 2026
Gemma 3 27B0.0%IndependentEpoch AI27 Aug 2026
Gemma 3 4B0.0%IndependentEpoch AI28 Aug 2026
GLM-4.7-Flash
Z.ai (Zhipu AI) · None effort
0.0%IndependentEpoch AI28 Aug 2026
GLM-4.7-Flash0.0%IndependentEpoch AI28 Aug 2026
GPT-3.5 Turbo0.0%IndependentEpoch AI7 Aug 2026
GPT-4o mini0.0%IndependentEpoch AI15 Jul 2026
gpt-oss-20b
OpenAI · High effort
0.0%IndependentEpoch AI27 Aug 2026
Granite 4.0 1B (Nano)0.0%IndependentEpoch AI30 Aug 2026
Granite 4.0 350M (Nano)0.0%IndependentEpoch AI28 Aug 2026
Granite 4.0 Micro (3B)0.0%IndependentEpoch AI30 Aug 2026
Llama 3 8B0.0%IndependentEpoch AI28 Aug 2026
Llama 3.1 8B0.0%IndependentEpoch AI27 Aug 2026
Llama 3.2 1B0.0%IndependentEpoch AI30 Aug 2026
Mistral 7B v0.30.0%IndependentEpoch AI30 Aug 2026
Qwen2.5-32B-Instruct0.0%IndependentEpoch AI30 Aug 2026
Qwen2.5-7B-Instruct0.0%IndependentEpoch AI30 Aug 2026
Qwen3-1.7B
Alibaba Group · None effort
0.0%IndependentEpoch AI28 Aug 2026
Qwen3-14B
Alibaba Group · None effort
0.0%IndependentEpoch AI30 Aug 2026
Qwen3-8B
Alibaba Group · None effort
0.0%IndependentEpoch AI27 Aug 2026
Qwen3.5-2B
Alibaba Group · None effort
0.0%IndependentEpoch AI28 Aug 2026
  • Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks, CC BY 4.0.

Sources