SWE-Together Benchmark

What is SWE-Together?

SWE-Together evaluates coding agents in multi-turn interactive user sessions reconstructed from real user-agent interactions. It comprises 109 repository-level…

Released

2026-06-29

Evaluates

Agents, Agents & Tool Use, Software & AI Compute

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.29957

SWE-Together paper and code

• Paper https://arxiv.org/abs/2606.29957
• Code https://github.com/Togetherbench/SWE-Together

Which sources cite SWE-Together?

• SWE-Together

Related Agents, Agents & Tool Use, Software & AI Compute benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• A3S-Bench
• Active-SWE
• AdaPlanBench
• Adaptive Adversaries
• ADeptS-Bench
• AeroCopilotBench
• AFT-Bench