Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multitask Language Understanding on MMLU-Pro (exact_match)
Loading...
18
Exact Match Accuracy
Baseline
15.92
16.46
17
17.54
Mar 15, 2026
Exact Match Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Exact Match Accuracy
Baseline
Base Model=Llama 3.2 1...
2026.03
18
Vocab. Trimming
Base Model=Llama 3.2 1...
2026.03
18
FlashHead
Base Model=Llama 3.2 1...
2026.03
18
SVDSoftmax
Base Model=Llama 3.2 1...
2026.03
16
Feedback
Search any
task
Search any
task
