Bug Hunt Bench - LMS: leaderboard
Metric: Planted Bugs Fixed (out of 60). Source: bughunt.productcompass.pm. 69 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.6 Sol (Max) | 24.5 |
| 2 | Claude Fable 5.1 (Max) | 24 |
| 3 | GPT-6 (Max) | 23 |
| 4 | GPT-5.6 Sol (xHigh) | 21 |
| 5 | GPT-5.6 Sol (High) | 21 |
| 6 | GPT-6 (xHigh) | 20 |
| 7 | Muse Spark 1.3 (Max) | 18 |
| 8 | Claude Fable 5.1 (High) | 18 |
| 9 | Kimi K3 | 17 |
| 10 | Claude Fable 5 (Max) | 17 |
| 11 | Grok 4.6 (xHigh) | 17 |
| 12 | GPT-5.6 Luna (Max) | 16 |
| 13 | GPT-5.6 Terra (Max) | 16 |
| 14 | Grok 4.6 (High) | 16 |
| 15 | GPT-5.6 Sol (Medium) | 16 |
Interactive version: theaggregate.ai/benchmark?slug=bug-hunt-bench-lms · How It Works · Data refreshed daily, snapshot 2026-09-19.