Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Feature Matching on GPT2 Layer 5 match with Layer 6
Loading...
2.53
LLM Eval
Semantic Optimal Transport
1.1572
1.5136
1.87
2.2264
May 27, 2026
LLM Eval
Accuracy
Cross-Entropy
Vector Error
Updated 6d ago
Evaluation Results
Method
Method
Links
LLM Eval
Accuracy
Cross-Entropy
Vector Error
Semantic Optimal Transport
2026.05
2.53
68.2
3.775
98.66
FeatFlow
2026.05
2.46
66.2
3.774
98.66
Match
2026.05
2.25
55.6
3.776
98.67
Attrib
2026.05
1.21
8.6
3.785
98.63
Feedback
Search any
task
Search any
task