SWE-PolyBench: leaderboard
Polyglot software-engineering benchmark with Java, Python, JavaScript, and TypeScript tasks plus retrieval/localization diagnostics.
Metric: Score (%). Source: huggingface.co. 1 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | iSWE-Agent | 0 |
Interactive version: theaggregate.ai/benchmark?slug=swe-polybench · How It Works · Data refreshed daily, snapshot 2026-09-05.