Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Performance Shift Correlation on MMLU-Pro
Loading...
0.9
STS (Act)
STS
0.588
0.669
0.75
0.831
Mar 3, 2026
STS (Act)
STS (ICL)
Updated 3mo ago
Evaluation Results
Method
Method
Links
STS (Act)
STS (ICL)
STS
Model=Qwen2.5-7B
2026.03
0.9
0.78
STS
Model=LLaMA3-8B
2026.03
0.71
0.81
STS
Model=Gemma2-9B
2026.03
0.6
0.77
Feedback
Search any
task
Search any
task
