Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Causal Reasoning on CausalT5K (L2)
Loading...
0.9
Collapse Rate
Claude Sonnet 4.5
0.244
4.672
9.1
13.528
Feb 12, 2026
Collapse Rate
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Collapse Rate
Accuracy
Claude Sonnet 4.5
zero-shot=true
2026.02
0.9
98.5
GPT-5.2
zero-shot=true
2026.02
3.7
96.3
Gemini 2.5 Flash
zero-shot=true
2026.02
7.7
92.3
GPT-4 Turbo
zero-shot=true
2026.02
12.5
87.5
GPT-3.5 Turbo
zero-shot=true
2026.02
17.3
82.9
Feedback
Search any
task
Search any
task