SWE-Explore - File Hit Rate: leaderboard

Metric: File-level hit rate (%; share of ground-truth files that the returned regions touch) on 848 repository-exploration instances (issues from 203 repositories in 10 languages): given the repository and issue, the explorer returns five ranked code regions, scored against line-level core context distilled from independent successful repair trajectories; the Mini-SWE-Agent scaffold with each LLM; higher is better. Source: arxiv.org. Saturation forecast: Around November 2027. 6 models tracked.

Top models

#ModelScore
1GPT-5.465.5
2GPT-5.4 Mini64.9
3Claude Sonnet 4.553.5
4Kimi K2.650.9
5Gemini 3 Pro36.9
6GLM-4.734.3

Interactive version: theaggregate.ai/benchmark?slug=swe-explore-file-hit-rate · How It Works · Data refreshed daily, snapshot 2026-09-29.