SWE-Explore - Precision: leaderboard
Metric: Line-level precision (%; share of returned lines inside the core context) 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 February 2028. 6 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5.4 | 54.2 |
| 2 | Claude Sonnet 4.5 | 51.9 |
| 3 | GPT-5.4 Mini | 50.9 |
| 4 | Kimi K2.6 | 47.5 |
| 5 | Gemini 3 Pro | 42 |
| 6 | GLM-4.7 | 41.4 |
Interactive version: theaggregate.ai/benchmark?slug=swe-explore-precision · How It Works · Data refreshed daily, snapshot 2026-09-29.