SWE-bench Live Java (102 tasks, SWE-agent): leaderboard
Metric: Resolved rate (%). Source: swe-bench-live.github.io. Saturation forecast: Around October 2027. 2 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.5 (Medium) | 50 |
| 2 | DeepSeek V4 Pro | 39.22 |
Interactive version: theaggregate.ai/benchmark?slug=swe-bench-live-java-102-tasks-swe-agent · How It Works · Data refreshed daily, snapshot 2026-09-26.