CodeRouterBench (OOD): leaderboard
CodeRouterBench out-of-distribution split: resolve rate % over 176 unseen repository tasks (featurebench-style bug fixing / feature work) for the same 8 models.
Metric: Resolve Rate (%). Source: huggingface.co. Saturation forecast: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5.4 | 64.2 | #83 |
| 2 | Claude Opus 4.6 | 63.64 | #67 |
| 3 | GLM-5 | 44.89 | #149 |
| 4 | Claude Sonnet 4.6 | 43.18 | #94 |
| 5 | MiniMax-M2.7 | 35.23 | #270 |
| 6 | Qwen 3 Max | 32.95 | #213 |
| 7 | Qwen 3.5 Plus | 27.27 | #133 |
| 8 | Kimi K2.5 | 19.89 | #152 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=coderouterbench-ood · How It Works · Data refreshed daily, snapshot 2026-11-05.