SnorkelUnderwrite 2.0 pass@5
Professional Work
Published pass@5 on the 200-task SnorkelUnderwrite 2.0 release; a correlated diagnostic of the pass@1 leaderboard.
Top models (higher is better)
| Model | Score |
|---|---|
| Grok 4.7 | 51.6 |
| GLM-5.3 | 51.3 |
| Kimi K3 | 50.8 |
| Claude Opus 5.5 | 39.4 |
| Claude Fable 5.1 | 38.4 |
| Gemini 3.8 Flash | 35.0 |
| GPT-6 Astra | 35.0 |
| Claude Opus 5 | 34.0 |
| Muse Spark 1.3 | 32.7 |
| Grok 4.6 | 31.3 |