RevengeBench - RobotRumble: leaderboard
Metric: Distance reduction (%; best round, mini-SWE-agent). Source: revengebench.com. Saturation forecast: Around June 2027. 12 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.1 | 71.1 |
| 2 | GPT-5 | 71 |
| 3 | GPT-5.5 | 65.2 |
| 4 | DeepSeek V4 Pro | 62.5 |
| 5 | Kimi K2.6 | 61.5 |
| 6 | GPT-5.4 Mini | 37.4 |
| 7 | DeepSeek V4 Flash | 30.5 |
| 8 | Gemma 4 31B | 30.5 |
| 9 | Qwen 3.6 35B A3B | 26.1 |
| 10 | Grok 4.1 Fast | 19.2 |
| 11 | GPT-OSS-120B | 9.5 |
| 12 | Gemma 4 26B A4B | 4.8 |
Interactive version: theaggregate.ai/benchmark?slug=revengebench-robotrumble · How It Works · Data refreshed daily, snapshot 2026-10-02.