Bug Hunt Bench: leaderboard
Metric: Planted Bugs Fixed (out of 105). Source: bughunt.productcompass.pm. 69 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-6 (Max) | 45 |
| 2 | GPT-5.6 Sol (Max) | 43.5 |
| 3 | Claude Fable 5.1 (Max) | 43 |
| 4 | GPT-6 (xHigh) | 43 |
| 5 | GPT-5.6 Sol (xHigh) | 39 |
| 6 | GPT-6 (High) | 35 |
| 7 | GPT-5.6 Sol (High) | 34 |
| 8 | GPT-6 (Medium) | 34 |
| 9 | GPT-5.6 Luna (Max) | 33 |
| 10 | Claude Fable 5.1 (High) | 33 |
| 11 | Muse Spark 1.3 (Max) | 32.2 |
| 12 | GPT-5.6 Terra (Max) | 32 |
| 13 | GPT-5.6 Sol (Medium) | 29 |
| 14 | Claude Fable 5 (Max) | 29 |
| 15 | Claude Fable 5.1 (xHigh) | 29 |
Interactive version: theaggregate.ai/benchmark?slug=bug-hunt-bench · How It Works · Data refreshed daily, snapshot 2026-09-19.