OdinEval: leaderboard
Metric: Resolved rate (%; share of 168 filtered Odin issues whose single generated unified patch applies, builds and passes the issue-specific regression test and the declared non-target checks; patch-only protocol with a fixed supplied source scope, no feedback, one attempt). Source: arxiv.org. Saturation forecast: Around 2029. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Kimi K3 | 66.7 |
| 2 | GLM-5.2 | 57.7 |
| 3 | GPT-5.6 Sol | 50.6 |
| 4 | Qwen 3.8 Max | 48.8 |
| 5 | GPT-5.6 Terra (Max) | 48.8 |
| 6 | MiniMax-M3 | 45.8 |
Interactive version: theaggregate.ai/benchmark?slug=odineval · How It Works · Data refreshed daily, snapshot 2026-09-26.