HF RL Explorer

PrimeIntellect/SWE-rebench-V2-Filtered-Easy-Verified

SWE-rebench-V2-Filtered-Easy-Verified: Verifiers environment on Hugging Face. Easy slice of PrimeIntellect/SWE-rebench-V2-Filtered-Verified: rows whose upstream LLM-judge difficulty is easy (implementation-time estimate < 15 min). Useful as a lower-variance starting pool for RL curricula.

PrimeIntellect/SWE-rebench-V2-Filtered-Easy-Verified on the Hugging Face Hub