SelfBench - datacurve/deep-swe-1-1: leaderboard
Metric: Task success (%) on 113 tasks of the datacurve/deep-swe-1-1 benchmark, run by SelfBench. Source: selfbench.dev. Saturation forecast: Around March 2027. 4 models tracked. Updated 18 Nov 2026.
Top models
| # | Model | Setting | Score | Overall rank |
|---|---|---|---|---|
| 1 | GPT-6.1 Sol | xHigh | 75.22 | #12 |
| 2 | Claude Opus 5.5 | xHigh | 69.03 | #6 |
| 3 | Dari Router | Default | 65.49 | |
| 4 | GPT-6 Luna | High | 39.82 | #102 |
No result here: #1 Claude Fable 5.2, #2 GPT-6.2 Astra, #3 Gemini 4 Carbon.
Interactive version: theaggregate.ai/benchmark?slug=selfbench-datacurve-deep-swe-1-1 · How It Works · Data refreshed daily, snapshot 2026-11-18.