Multi-Hop Question Answering on HotpotQA (Score)
38.9HotpotQA Scoreπ-Play
Evaluation Results
| Method | Links | |
|---|---|---|
| π-PlayBase Model=Qwen3-8B2026.04 | 38.9 | |
| π-PlayBase Model=Qwen3-4B-Instruct-25072026.04 | 38.5 | |
| Dr.ZeroBase Model=Qwen3-4B-Instruct-25072026.04 | 38.4 | |
| Dr.ZeroBase Model=Qwen3-8B2026.04 | 36.6 | |
| Search-R1Base Model=Qwen3-4B-Instruct-25072026.04 | 34.9 | |
| SQLM*Base Model=Qwen3-4B-Instruct-25072026.04 | 34.1 | |
| SQLM*Base Model=Qwen3-8B2026.04 | 33.1 | |
| SQLM*Base Model=Qwen3-4B2026.04 | 33 | |
| π-PlayBase Model=Qwen3-4B2026.04 | 32.3 | |
| Search-R1Base Model=Qwen3-8B2026.04 | 32 | |
| Dr.ZeroBase Model=Qwen3-4B2026.04 | 31 | |
| Search-R1Base Model=Qwen3-4B2026.04 | 30.7 | |
| ReActBase Model=Qwen3-4B-Instruct-25072026.04 | 22.8 | |
| ReActBase Model=Qwen3-8B2026.04 | 22.3 | |
| ReActBase Model=Qwen3-4B2026.04 | 11.2 |