Logic Reasoning on Autologic en
0.439ScoreDARL
Evaluation Results
| Method | Links | |
|---|---|---|
| DARLBase=Base, Verifier=✗2026.01 | 0.439 | |
| DARLBase=Inst, Verifier=✗2026.01 | 0.42 | |
| Qwen2.5-7B-InstBase=Base, Verifier=-2026.01 | 0.406 | |
| VeriFreeBase=Base, Verifier=✗2026.01 | 0.395 | |
| RLPRBase=Inst, Verifier=✗2026.01 | 0.349 | |
| RLPRBase=Base, Verifier=✗2026.01 | 0.319 | |
| SimpleRL-ZooBase=Base, Verifier=Rule2026.01 | 0.312 | |
| General ReasonerBase=Base, Verifier=Model2026.01 | 0.29 | |
| Llama3.1-8B-InstBase=Inst, Verifier=-2026.01 | 0.251 | |
| RLVRBase=Base, Verifier=Rule2026.01 | 0.224 | |
| RLVRBase=Inst, Verifier=Rule2026.01 | 0.202 | |
| Oat-ZeroBase=Math, Verifier=Rule2026.01 | 0.191 | |
| SimpleRL-ZooBase=Math, Verifier=Rule2026.01 | 0.144 | |
| TTRLBase=Base, Verifier=Rule2026.01 | 0.128 | |
| Qwen2.5-7BBase=-, Verifier=-2026.01 | 0.084 | |
| PRIMEBase=Math, Verifier=Rule2026.01 | 0.012 |