Chess Puzzles (Epoch AI) — leaderboard

Chess puzzle-solving benchmark evaluated by Epoch AI. Tests tactical pattern recognition, calculation depth, and strategic reasoning across a range of puzzle difficulties.

Metric: Accuracy (%). Source: epoch.ai. Status: saturation imminent. 57 models tracked.

Top models

#ModelScore
1GPT-5.5 Pro (xHigh)64
2GPT-5.4 Pro (xHigh)58.6
3Gemini 3.1 Pro (Preview)55
4GPT-5.6 Sol (Max)55
5GPT-5.5 (xHigh)54
6GPT-5.6 Terra (Max)54
7Gemini 3.5 Flash (High)50
8GPT-5.2 (xHigh)49
9GPT-5.4 (xHigh)44
10Claude Fable 5 (Max)41
11GPT-5.2 (Medium)40
12GPT-5.2 (High)40
13GPT-5.6 Luna (Max)40
14Kimi K3 (Max)39
15Gemini 3 Flash (Preview)38

Interactive version: theaggregate.ai/benchmark?slug=chess-puzzles-epoch-ai · How the rankings work · Data refreshed daily, snapshot 2026-07-22.