SREGym: Can AI agents resolve production issues? Real-world SRE problems including metastable failures, misconfigurations, and many more. Live system environments. From the University of Illinois at Urbana-Champaign. To submit, open an issue with the submission label at github.com/SREGym/SREGym.
top agent performance
clean · top 3
| Rank | Agent | Model | E2E (%) |
|---|---|---|---|
| 1 | GitHub Copilot | GPT-5.6 Sol (max) | 72.2 |
| 2 | GitHub Copilot | Claude Sonnet 5 (medium) | 70.7 |
| 3 | GitHub Copilot | GPT-5.5 (max) | 70.0 |
with noises · top 3
| Rank | Agent | Model | E2E (%) |
|---|---|---|---|
| 1 | Claude Code | Claude Sonnet 4.6 | 53.7 |
| 2 | Codex | GPT-5.4 | 45.9 |
| 3 | Stratus | Claude Sonnet 4.6 | 39.6 |