Causal Reasoning on BBEH
55.2Accuracy (Causal Reasoning)UNICO
Evaluation Results
| Method | Links | |
|---|---|---|
| UNICOBase Model=Qwen3-4B, Data=UNICO2026.05 | 55.2 | |
| UNICOBase Model=Qwen3-8B, Data=UNICO2026.05 | 54.5 | |
| Olmo3.1-32B-InstructBase Model=Olmo3.1-32B-Instruct2026.05 | 54 | |
| UNICOBase Model=Olmo3-7B-Instruct, Data=UNICO2026.05 | 51 | |
| Qwen3-32BBase Model=Qwen3-32B2026.05 | 50.3 | |
| CauGymBase Model=Qwen3-8B, Data=CauGym2026.05 | 50 | |
| OriginalBase Model=Olmo3-7B-Instruct, Data=Original2026.05 | 48.8 | |
| CDCRBase Model=Qwen3-8B, Data=CDCR2026.05 | 47.2 | |
| CauGymBase Model=Qwen3-4B, Data=CauGym2026.05 | 47 | |
| OriginalBase Model=Qwen3-8B, Data=Original2026.05 | 47 | |
| OriginalBase Model=Qwen3-4B, Data=Original2026.05 | 46 | |
| CDCRBase Model=Olmo3-7B-Instruct, Data=CDCR2026.05 | 45.2 | |
| CauGymBase Model=Olmo3-7B-Instruct, Data=CauGym2026.05 | 45 | |
| CDCRBase Model=Qwen3-4B, Data=CDCR2026.05 | 43 |