CodeClash - BattleSnake: leaderboard
CodeClash arena where LLMs iteratively develop Python bots for a grid-based survival game, competing to find food and outlast rival snakes across multi-round tournaments.
Metric: ELO. Source: codeclash.ai. Saturation forecast: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude Sonnet 4.5 | 1470 | #142 |
| 2 | GPT-5 Mini | 1370 | #186 |
| 3 | O3 | 1358 | #124 |
| 4 | GPT-5 | 1339 | #98 |
| 5 | Claude Sonnet 4 | 1254 | #199 |
| 6 | Gemini 2.5 Pro | 1116 | #152 |
| 7 | Grok Code Fast 1 | 833 | #337 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=codeclash-battlesnake · How It Works · Data refreshed daily, snapshot 2026-10-20.