EvoCode-Bench — leaderboard
Metric: MT@4 (self-reported). Source: benchmarklist.com. 13 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 4.7 | 54 |
| 2 | GPT-5.5 | 52.4 |
| 3 | Claude Opus 4.6 | 44 |
| 4 | GLM-5.1 | 36.2 |
| 5 | Qwen 3.6 Plus | 29.4 |
| 6 | MiMo-V2.5 | 17.3 |
| 7 | Gemini 3.1 Pro (Preview) | 13.7 |
| 8 | Qwen 3.5 397B A17B | 4.6 |
| 9 | MiniMax-M2.7 | 3.7 |
Interactive version: theaggregate.ai/benchmark?slug=evocode-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.