Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Causal Reasoning on BBEH
Loading...
55.2
Accuracy (Causal Reasoning)
UNICO
42.512
45.806
49.1
52.394
May 24, 2026
Accuracy (Causal Reasoning)
Updated 8d ago
Evaluation Results
Method
Method
Links
Accuracy (Causal Reasoning)
UNICO
Base Model=Qwen3-4B, D...
2026.05
55.2
UNICO
Base Model=Qwen3-8B, D...
2026.05
54.5
Olmo3.1-32B-Instruct
Base Model=Olmo3.1-32B...
2026.05
54
UNICO
Base Model=Olmo3-7B-In...
2026.05
51
Qwen3-32B
Base Model=Qwen3-32B
2026.05
50.3
CauGym
Base Model=Qwen3-8B, D...
2026.05
50
Original
Base Model=Olmo3-7B-In...
2026.05
48.8
CDCR
Base Model=Qwen3-8B, D...
2026.05
47.2
CauGym
Base Model=Qwen3-4B, D...
2026.05
47
Original
Base Model=Qwen3-8B, D...
2026.05
47
Original
Base Model=Qwen3-4B, D...
2026.05
46
CDCR
Base Model=Olmo3-7B-In...
2026.05
45.2
CauGym
Base Model=Olmo3-7B-In...
2026.05
45
CDCR
Base Model=Qwen3-4B, D...
2026.05
43
Feedback
Search any
task
Search any
task