SolBehave - Compile@10 - One Repair: leaderboard
SolBehave - Compile@10 - One Repair. Mean fraction of ten generated samples per contract that compile; not any-success pass@10. One Repair uses a single compiler-feedback repair. Reported metric: Compiling samples (%). Primary published table, with source configuration boundaries preserved.
Metric: Compiling samples (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemma 4 31B | 92.7 | #195 |
| 2 | Qwen 3.6 27B | 71.3 | #166 |
| 3 | Gemma 4 12B | 57.9 | #560 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #7 Gemini 4 Argon.
Interactive version: theaggregate.ai/benchmark?slug=solbehave-compile-10-one-repair · How It Works · Data refreshed daily, snapshot 2026-10-16.