ChessBench LLM: leaderboard
Evaluates LLM chess ability using Glicko-2 ratings calibrated with engine anchors. Tracks win/loss/draw records, move legality percentage, and cost per game.
Metric: Lichess-Classical-calibrated Glicko-2 rating (native signed points). Source: chessbenchllm.onrender.com. 136 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Best Expert | 2236 | |
| 2 | Gemini 3.1 Pro (Preview) (High) | 2144 | #58 (Gemini 3.1 Pro (Preview)) |
| 3 | Gemini 3.1 Pro (Preview) (Medium) | 2028 | #58 (Gemini 3.1 Pro (Preview)) |
| 4 | Gemini 4 Argon (High) | 2022 | #8 (Gemini 4 Argon) |
| 5 | GPT-6 Astra (High) | 1975 | #6 (GPT-6 Astra) |
| 6 | Gemini 3 Pro (Preview) (High) | 1953 | #66 (Gemini 3 Pro (Preview)) |
| 7 | Gemini 3.5 Flash (Medium) | 1944 | #60 (Gemini 3.5 Flash) |
| 8 | Gemini 3.6 Flash (Medium) | 1916 | #51 (Gemini 3.6 Flash) |
| 9 | Gemini 3.8 Flash (High) | 1877 | #21 (Gemini 3.8 Flash) |
| 10 | Gemini 3 Flash (Preview) (Medium) | 1857 | #82 (Gemini 3 Flash (Preview)) |
| 11 | GPT-6 Astra (Medium) | 1779 | #6 (GPT-6 Astra) |
| 12 | Gemini 3 Flash (Preview) (High) | 1750 | #82 (Gemini 3 Flash (Preview)) |
| 13 | Median Expert | 1542 | |
| 14 | GPT-5.6 Sol (High) | 1532 | #19 (GPT-5.6 Sol) |
| 15 | GPT-6.1 Sol (High) | 1490 | #7 (GPT-6.1 Sol) |
No result here: #10 Muse Wonder Full.
Interactive version: theaggregate.ai/benchmark?slug=chessbench-llm · How It Works · Data refreshed daily, snapshot 2026-10-20.