SWE-Together Benchmark
Explore score history ↗SWE-Together evaluates coding agents in multi-turn interactive user sessions reconstructed from real user-agent interactions. It comprises 109 repository-level tasks with a reactive LLM-based user simulator, measuring final repository correctness and the number of corrective feedback turns.
- Released
- 2026-06-29
- Evaluates
- Agents, Agents & Tool Use, Software & AI Compute
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SWE-Together paper and code
No reported scores are on record for this benchmark yet.