RevengeBench - BattleSnake: leaderboard

Metric: Distance reduction (%; best round, mini-SWE-agent). Source: revengebench.com. Saturation forecast: Around August 2027. 12 models tracked.

Top models

#ModelScore
1GPT-577.6
2GPT-5.573.5
3DeepSeek V4 Pro72.3
4Kimi K2.670.6
5GLM-5.170.5
6Gemma 4 31B66.4
7Gemma 4 26B A4B64.9
8DeepSeek V4 Flash60.9
9GPT-5.4 Mini51.5
10Qwen 3.6 35B A3B48.9
11Grok 4.1 Fast41.3
12GPT-OSS-120B40.8

Interactive version: theaggregate.ai/benchmark?slug=revengebench-battlesnake · How It Works · Data refreshed daily, snapshot 2026-10-02.