# Danau5tin/terminal-bench-rl

<https://repo.masters-masters.com/en/repos/Danau5tin/terminal-bench-rl>

[Home](https://repo.masters-masters.com/en) › [Danau5tin](https://repo.masters-masters.com/en/owners/Danau5tin) › [terminal-bench-rl](https://repo.masters-masters.com/en/repos/Danau5tin/terminal-bench-rl)

Danau5tin/terminal-bench-rl has 419 stars on GitHub. Its RepoMasters card: Alpha tier. GRPO training code which scales to 32xH100s for long horizon…

| Field | Value |
| --- | --- |
| Owner | [Danau5tin](https://repo.masters-masters.com/en/owners/Danau5tin) |
| Stars | 419 |
| Forks | 25 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | None |
| Created | 2025 |
| Tier | [Alpha (250 to 699 ★)](https://repo.masters-masters.com/en/ranks/b_movie) |
| View on GitHub | [Danau5tin/terminal-bench-rl](https://github.com/Danau5tin/terminal-bench-rl) |

## Repository

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.

The tier for repos with 250 to 699 ★. Published odds per card pulled: 20%. Rarity: Uncommon.

## More repos by Danau5tin

- [Danau5tin/multi-agent-coding-system · ★ 1,472 · Python · Beta](https://repo.masters-masters.com/en/repos/Danau5tin/multi-agent-coding-system)
- [Danau5tin/ai-trains-ai · ★ 243 · Python · Prototype](https://repo.masters-masters.com/en/repos/Danau5tin/ai-trains-ai)
- [Danau5tin/Orca-Agent-RL · ★ 104 · Python · Prototype](https://repo.masters-masters.com/en/repos/Danau5tin/Orca-Agent-RL)

## Nearby in Python

- [hybridops-tech/hybridops-core · ★ 419 · Python · Alpha](https://repo.masters-masters.com/en/repos/hybridops-tech/hybridops-core)
- [andreisss/KslDump · ★ 419 · Python · Alpha](https://repo.masters-masters.com/en/repos/andreisss/KslDump)
- [tmchow/illo-skill · ★ 419 · Python · Alpha](https://repo.masters-masters.com/en/repos/tmchow/illo-skill)
- [nipy/nipy · ★ 419 · Python · Alpha](https://repo.masters-masters.com/en/repos/nipy/nipy)
- [FanfouAPI/FanFouAPIDoc · ★ 419 · Python · Alpha](https://repo.masters-masters.com/en/repos/FanfouAPI/FanFouAPIDoc)
- [sch3m4/androidpatternlock · ★ 419 · Python · Alpha](https://repo.masters-masters.com/en/repos/sch3m4/androidpatternlock)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.