Causal Reasoning on ExecCF
80.4AccuracyUNICO
Evaluation Results
| Method | Links | |
|---|---|---|
| UNICOBase Model=Qwen3-8B, Data=UNICO2026.05 | 80.4 | |
| UNICOBase Model=Qwen3-4B, Data=UNICO2026.05 | 76.7 | |
| UNICOBase Model=Olmo3-7B-Instruct, Data=UNICO2026.05 | 72.8 | |
| CauGymBase Model=Qwen3-8B, Data=CauGym2026.05 | 69.6 | |
| Olmo3.1-32B-InstructBase Model=Olmo3.1-32B-Instruct2026.05 | 65.2 | |
| Qwen3-32BBase Model=Qwen3-32B2026.05 | 61.5 | |
| OriginalBase Model=Qwen3-8B, Data=Original2026.05 | 60.1 | |
| OriginalBase Model=Olmo3-7B-Instruct, Data=Original2026.05 | 59.9 | |
| OriginalBase Model=Qwen3-4B, Data=Original2026.05 | 59.3 | |
| CauGymBase Model=Qwen3-4B, Data=CauGym2026.05 | 58.6 | |
| CauGymBase Model=Olmo3-7B-Instruct, Data=CauGym2026.05 | 54.1 | |
| CDCRBase Model=Olmo3-7B-Instruct, Data=CDCR2026.05 | 50.5 | |
| CDCRBase Model=Qwen3-8B, Data=CDCR2026.05 | 36.6 | |
| CDCRBase Model=Qwen3-4B, Data=CDCR2026.05 | 32.4 |