Causal Reasoning on Com2
79.8AccuracyQwen3-32B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-32BBase Model=Qwen3-32B2026.05 | 79.8 | |
| Olmo3.1-32B-InstructBase Model=Olmo3.1-32B-Instruct2026.05 | 79.6 | |
| UNICOBase Model=Qwen3-8B, Data=UNICO2026.05 | 78.3 | |
| OriginalBase Model=Olmo3-7B-Instruct, Data=Original2026.05 | 77.6 | |
| CauGymBase Model=Qwen3-8B, Data=CauGym2026.05 | 77.2 | |
| UNICOBase Model=Olmo3-7B-Instruct, Data=UNICO2026.05 | 76.7 | |
| CauGymBase Model=Olmo3-7B-Instruct, Data=CauGym2026.05 | 76.5 | |
| CDCRBase Model=Olmo3-7B-Instruct, Data=CDCR2026.05 | 75.7 | |
| OriginalBase Model=Qwen3-8B, Data=Original2026.05 | 75.5 | |
| UNICOBase Model=Qwen3-4B, Data=UNICO2026.05 | 74.6 | |
| OriginalBase Model=Qwen3-4B, Data=Original2026.05 | 72.9 | |
| CauGymBase Model=Qwen3-4B, Data=CauGym2026.05 | 72.6 | |
| CDCRBase Model=Qwen3-8B, Data=CDCR2026.05 | 70.2 | |
| CDCRBase Model=Qwen3-4B, Data=CDCR2026.05 | 69.5 |