SWE-bench Live Full (SWE-agent): leaderboard
Metric: Resolved rate (%). Source: swe-bench-live.github.io. Saturation forecast: Estimated already saturated. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-4.1 | 18.57 |
| 2 | Claude 3.7 Sonnet (20250219) | 17.13 |
| 3 | GPT-4o (2024-11-20) | 9.1 |
Interactive version: theaggregate.ai/benchmark?slug=swe-bench-live-full-swe-agent · How It Works · Data refreshed daily, snapshot 2026-09-26.