SWE-bench Live Lite (Agentless): leaderboard
Metric: Resolved rate (%). Source: swe-bench-live.github.io. Saturation forecast: Around 2029. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3 (0324) | 13.33 |
| 2 | GPT-4.1 | 12 |
| 3 | GPT-4o (2024-11-20) | 11.67 |
| 4 | Claude 3.7 Sonnet (20250219) | 11.33 |
Interactive version: theaggregate.ai/benchmark?slug=swe-bench-live-lite-agentless · How It Works · Data refreshed daily, snapshot 2026-09-26.