Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Binary comparison for commonsense plausibility on ViComTe Shape 1.0 (test)
Loading...
94.33
Accuracy
EVA-CLIP
89.0364
90.4107
91.785
93.1593
Feb 19, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
EVA-CLIP
Framework=ComPaSS
2025.02
94.33
Qwen2
Framework=ComPaSS, Tra...
2025.02
94.04
Mistral
Framework=ComPaSS, Tra...
2025.02
91.5
GPT-3.5
2025.02
90.08
GPT-4
2025.02
89.24
Feedback
Search any
task
Search any
task
