Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Causal Variable Identification on COCO
Loading...
73.6
F1 (X)
Llama4-M
62.16
65.13
68.1
71.07
May 17, 2025
F1 (X)
F1 (Z)
F1 (M)
F1 (Y)
Updated 4d ago
Evaluation Results
Method
Method
Links
F1 (X)
F1 (Z)
F1 (M)
F1 (Y)
Llama4-M
Setting=Decompositiona...
2025.05
73.6
71.7
67.4
73.5
GPT-o4
Setting=Decompositiona...
2025.05
73.2
71.1
68
74.4
GPT-5
Setting=Decompositiona...
2025.05
72.8
70.2
67.3
73.4
Llama4-S
Setting=Decompositiona...
2025.05
72.5
70.8
66.2
72.1
Qwen3
Setting=Decompositiona...
2025.05
67.2
65.4
54.2
61.8
DeepSeek
Setting=Decompositiona...
2025.05
65.9
63.2
55.7
62.6
Gemini2.5
Setting=Decompositiona...
2025.05
62.6
60.9
52.8
58.3
Feedback
Search any
task
Search any
task