LLM Chess (Saplin) — leaderboard
Metric: ELO. Source: maxim-saplin.github.io. 141 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (Medium) | 1532.2 |
| 2 | GPT-5.5 (High) | 1528.4 |
| 3 | Gemini 3.1 Pro (Preview) (High) | 1511.4 |
| 4 | GPT-5.4 (High) | 1322.3 |
| 5 | GPT-5.4 (Medium) | 1252.9 |
| 6 | GPT-5 (Medium) | 1086.4 |
| 7 | GPT-5.2 (Medium) | 1085.1 |
| 8 | Gemini 3 Pro (Preview) (High) | 1033.7 |
| 9 | Gemini 3.5 Flash (Medium) | 952.9 |
| 10 | GPT-5.1 (Medium) | 947.6 |
| 11 | GPT-5 (Low) | 858.2 |
| 12 | Grok 4.20 (Reasoning) | 843 |
| 13 | Grok 4.1 Fast (Reasoning) | 799.5 |
| 14 | GPT-5.2 (Low) | 782.5 |
| 15 | O3 (Medium) | 777.6 |
Interactive version: theaggregate.ai/benchmark?slug=llm-chess-saplin · How the rankings work · Data refreshed daily, snapshot 2026-07-22.