AI Chess Leaderboard (Reasoning): leaderboard

LLMs play full chess games from the starting position. Ranked by Elo rating derived from head-to-head matches. Tests legal move generation, multi-step planning, and game-state tracking over 264 evaluated models.

Metric: Elo. Source: dubesor.de. Status: saturation imminent. 324 models tracked.

Top models

#ModelScore
1Gemini 3.1 Pro (Preview)1910
2Gemini 3.7 Flash1879
3Gemini 3 Pro (Preview)1850
4Gemini 3.8 Flash1849
5Qwen 3 Max (Thinking)1800
6GPT-5 Codex1777
7Gemini 3.5 Flash1755
8Gemini 3.6 Flash1752
9GPT-5.1 Codex1743
10GPT-5.51687
11Claude Fable 51645
12GPT-5.6 Pro Sol1617
13GPT-5.6 Sol1608
14Grok 41596
15DeepSeek V4 Flash (0731)1584

Interactive version: theaggregate.ai/benchmark?slug=ai-chess-leaderboard-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.