SWE-PolyBench Verified (Java) — leaderboard
Metric: Score (%). Source: huggingface.co. 3 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Atlassian Rovo Dev (2025-12-08) | 46.38 |
| 2 | iSWE-Agent | 46.38 |
| 3 | Prometheus-v1.2 + GPT-5 | 33.33 |
Interactive version: theaggregate.ai/benchmark?slug=swe-polybench-verified-java · How the rankings work · Data refreshed daily, snapshot 2026-07-22.