SelfBench - getsentry/sentry: leaderboard
Metric: Task success (%) on 43 tasks rebuilt from the repository's merged pull requests (hidden tests). Source: selfbench.dev. Saturation forecast: Around January 2027. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude Opus 5.5 (High) | 88.37 |
| 2 | Claude Sonnet 5.5 (High) | 88.37 |
| 3 | GPT-6.1 Sol (High) | 86.05 |
| 4 | Kimi K3 (High) | 83.72 |
| 5 | GPT-6.1 Sol (Low) | 79.07 |
| 6 | GPT-6 Luna (High) | 46.51 |
| 7 | GPT-6 Luna (Low) | 32.56 |
Interactive version: theaggregate.ai/benchmark?slug=selfbench-getsentry-sentry · How It Works · Data refreshed daily, snapshot 2026-10-03.