List your company

Causal Reasoning on BBEH

55.2Accuracy (Causal Reasoning)UNICO
42.51245.80649.152.394May 24, 2026

Evaluation results

MethodLinks
UNICOBase Model=Qwen3-4B, Data=UNICO2026.0555.2
UNICOBase Model=Qwen3-8B, Data=UNICO2026.0554.5
Olmo3.1-32B-InstructBase Model=Olmo3.1-32B-Instruct2026.0554
UNICOBase Model=Olmo3-7B-Instruct, Data=UNICO2026.0551
Qwen3-32BBase Model=Qwen3-32B2026.0550.3
CauGymBase Model=Qwen3-8B, Data=CauGym2026.0550
OriginalBase Model=Olmo3-7B-Instruct, Data=Original2026.0548.8
CDCRBase Model=Qwen3-8B, Data=CDCR2026.0547.2
CauGymBase Model=Qwen3-4B, Data=CauGym2026.0547
OriginalBase Model=Qwen3-8B, Data=Original2026.0547
OriginalBase Model=Qwen3-4B, Data=Original2026.0546
CDCRBase Model=Olmo3-7B-Instruct, Data=CDCR2026.0545.2
CauGymBase Model=Olmo3-7B-Instruct, Data=CauGym2026.0545
CDCRBase Model=Qwen3-4B, Data=CDCR2026.0543