Symbolic Reasoning on Coin Flip (OOD)
95.1pass@1RULEREASONER-8B + DADS
Evaluation Results
| Method | Links | |
|---|---|---|
| RULEREASONER-8B + DADSBackbone=Qwen3-8B, Algorithm=DADS2025.06 | 95.1 | |
| Qwen3-8B-BaseBackbone=Qwen3-8B2025.06 | 44.7 |
Loading the SOTA2 catalog…
| Method | Links | |
|---|---|---|
| RULEREASONER-8B + DADSBackbone=Qwen3-8B, Algorithm=DADS2025.06 | 95.1 | |
| Qwen3-8B-BaseBackbone=Qwen3-8B2025.06 | 44.7 |