AlphaUncommon
Danau5tin/terminal-bench-rl
GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.
- Owner
- Danau5tin (personal account)
- Stars
- Stars: 419
- Forks
- Forks: 25
- Language
- Python
- License
- None
- Created
- 2025
- Tier
- Alpha (250 to 699 ★) What this tier means
More repos by Danau5tin
All 4 repos by Danau5tin- Danau5tin/multi-agent-coding-systemStars: 1,472PythonBeta
- Danau5tin/ai-trains-aiStars: 243PythonPrototype
- Danau5tin/Orca-Agent-RLStars: 104PythonPrototype
Nearby in Python
All Python repos- hybridops-tech/hybridops-coreStars: 419PythonAlpha
- andreisss/KslDumpStars: 419PythonAlpha
- tmchow/illo-skillStars: 419PythonAlpha
- nipy/nipyStars: 419PythonAlpha
- FanfouAPI/FanFouAPIDocStars: 419PythonAlpha
- sch3m4/androidpatternlockStars: 419PythonAlpha