Gsm8k Multireward RL Env (Community)
Fresh
GSM8K with multi-reward support (correctness + length, optional gating)
- Type
- RL Env
- Capabilities
- Math
- Tags
- Multi Reward
- Runtime
single-turn- License
- apache-2.0
- Size
- v0.2.0
- Published
- Jan 2026
Cite
Notes
Only stored in your browser.
Lift evidence
1| Eval | Tools known to lift | Source paper |
|---|---|---|
| GSM8K | Gsm8k Multireward RL Env (Community) | - |