AI Chess Leaderboard (Continuation) — leaderboard
LLMs continue chess games from mid-game positions. Ranked by Elo rating derived from head-to-head matches across 211 evaluated models. Tests tactical calculation and endgame play from non-standard starting states.
Metric: Elo. Source: dubesor.de. Status: saturation imminent. 244 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3 Pro (Preview) | 1810 |
| 2 | GPT-4.5 (Preview) | 1800 |
| 3 | Gemini 3.6 Flash | 1782 |
| 4 | Gemini 3 Flash (Preview) | 1719 |
| 5 | Gemini 3.1 Pro (Preview) | 1690 |
| 6 | Gemini 3.5 Flash | 1650 |
| 7 | GPT-4o ChatGPT | 1584 |
| 8 | GPT-5.5 | 1523 |
| 9 | Gemini 3.5 Flash Lite | 1512 |
| 10 | GPT-5 | 1498 |
| 11 | GPT-4o | 1493 |
| 12 | GPT-5 Chat | 1465 |
| 13 | GPT-5.1 Codex | 1418 |
| 14 | Qwen 3 14B | 1409 |
| 15 | Gemini 3.1 Flash Lite (Preview) | 1408 |
Interactive version: theaggregate.ai/benchmark?slug=ai-chess-leaderboard-continuation · How the rankings work · Data refreshed daily, snapshot 2026-07-22.