Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Complexity Prediction on MMLU+MMLU-PRO+GSM8K
Loading...
89.1
ROC-AUC
IntroLM
73.708
77.704
81.7
85.696
Jan 7, 2026
ROC-AUC
PR-AUC
Updated 1mo ago
Evaluation Results
Method
Method
Links
ROC-AUC
PR-AUC
IntroLM
Backbone Model=Qwen3-8B
2026.01
89.1
63.4
DeBERTa-v3-Large
Number of Parameters=4...
2026.01
75.8
45.5
DeBERTa-v3-Base
Number of Parameters=1...
2026.01
74.3
44.3
Feedback
Search any
task
Search any
task
