Logic Reasoning on Autologic cn
40.3ScoreDARL
Evaluation Results
| Method | Links | |
|---|---|---|
| DARLBase=Base, Verifier=✗2026.01 | 40.3 | |
| DARLBase=Inst, Verifier=✗2026.01 | 39.2 | |
| Qwen2.5-7B-InstBase=Base, Verifier=-2026.01 | 38.3 | |
| VeriFreeBase=Base, Verifier=✗2026.01 | 35.7 | |
| General ReasonerBase=Base, Verifier=Model2026.01 | 29.2 | |
| RLPRBase=Base, Verifier=✗2026.01 | 29.1 | |
| SimpleRL-ZooBase=Base, Verifier=Rule2026.01 | 29 | |
| RLPRBase=Inst, Verifier=✗2026.01 | 27.8 | |
| RLVRBase=Base, Verifier=Rule2026.01 | 25.1 | |
| Llama3.1-8B-InstBase=Inst, Verifier=-2026.01 | 22 | |
| Oat-ZeroBase=Math, Verifier=Rule2026.01 | 13.3 | |
| TTRLBase=Base, Verifier=Rule2026.01 | 11.1 | |
| SimpleRL-ZooBase=Math, Verifier=Rule2026.01 | 7.1 | |
| Qwen2.5-7BBase=-, Verifier=-2026.01 | 5.9 | |
| PRIMEBase=Math, Verifier=Rule2026.01 | 2.9 | |
| RLVRBase=Inst, Verifier=Rule2026.01 | 2.3 |