Causal Reasoning on CaLM
73.9AccuracyUNICO
Evaluation Results
| Method | Links | |
|---|---|---|
| UNICOBase Model=Qwen3-8B, Data=UNICO2026.05 | 73.9 | |
| UNICOBase Model=Qwen3-4B, Data=UNICO2026.05 | 70.3 | |
| Olmo3.1-32B-InstructBase Model=Olmo3.1-32B-Instruct2026.05 | 70.1 | |
| Qwen3-32BBase Model=Qwen3-32B2026.05 | 69.2 | |
| CauGymBase Model=Qwen3-8B, Data=CauGym2026.05 | 67.1 | |
| CauGymBase Model=Qwen3-4B, Data=CauGym2026.05 | 65.5 | |
| UNICOBase Model=Olmo3-7B-Instruct, Data=UNICO2026.05 | 61.2 | |
| CauGymBase Model=Olmo3-7B-Instruct, Data=CauGym2026.05 | 60.6 | |
| OriginalBase Model=Qwen3-8B, Data=Original2026.05 | 60.4 | |
| OriginalBase Model=Qwen3-4B, Data=Original2026.05 | 59.3 | |
| OriginalBase Model=Olmo3-7B-Instruct, Data=Original2026.05 | 56.6 | |
| CDCRBase Model=Olmo3-7B-Instruct, Data=CDCR2026.05 | 54.6 | |
| CDCRBase Model=Qwen3-8B, Data=CDCR2026.05 | 51.6 | |
| CDCRBase Model=Qwen3-4B, Data=CDCR2026.05 | 46.3 |