List your company

Multi-Hop QA on HotpotQA (pass@1, Avg Rank)

33.5pass@1DAPO
10.116.17522.2528.325Apr 9, 2026

Evaluation results

MethodLinks
DAPO2026.0433.53
SEARL2026.0433.51.43
TIR Prompt2026.04235.29
GRPO2026.0421.52.43
ARPO2026.04143.57
Reinforce++2026.04114.57