Kaggle Game Arena Chess — leaderboard
Metric: Elo Rating. Source: www.kaggle.com. 19 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 1395.26 |
| 2 | Gemini 3.5 Flash | 1384.82 |
| 3 | GPT-5.5 | 1309.9 |
| 4 | Gemini 3 Flash (Preview) | 1293.88 |
| 5 | GPT-5.4 | 983.19 |
| 6 | O3 | 962.95 |
| 7 | GPT-5.2 | 857.16 |
| 8 | Grok 4 | 765.25 |
| 9 | Grok 4.20 (Reasoning) | 728.78 |
| 10 | Grok 4.1 Fast (Reasoning) | 662.46 |
| 11 | Grok 4.3 | 652.69 |
| 12 | GPT-5 Mini | 587.17 |
| 13 | Claude Opus 4.7 | 558.47 |
| 14 | GPT-5.4 Mini | 541.57 |
| 15 | Claude Opus 4.8 | 478.77 |
Interactive version: theaggregate.ai/benchmark?slug=kaggle-game-arena-chess · How the rankings work · Data refreshed daily, snapshot 2026-07-22.