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
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 1910 |
| 2 | Gemini 3.7 Flash | 1879 |
| 3 | Gemini 3 Pro (Preview) | 1850 |
| 4 | Gemini 3.8 Flash | 1849 |
| 5 | Qwen 3 Max (Thinking) | 1800 |
| 6 | GPT-5 Codex | 1777 |
| 7 | Gemini 3.5 Flash | 1755 |
| 8 | Gemini 3.6 Flash | 1752 |
| 9 | GPT-5.1 Codex | 1743 |
| 10 | GPT-5.5 | 1687 |
| 11 | Claude Fable 5 | 1645 |
| 12 | GPT-5.6 Pro Sol | 1617 |
| 13 | GPT-5.6 Sol | 1608 |
| 14 | Grok 4 | 1596 |
| 15 | DeepSeek V4 Flash (0731) | 1584 |
Interactive version: theaggregate.ai/benchmark?slug=ai-chess-leaderboard-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.