Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (exact_match)
Loading...
46
Exact Match Accuracy
Baseline
25.2
30.6
36
41.4
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
46
Vocab. Trimming
Base Model=Llama 3.2 1...
2026.03
46
FlashHead
Base Model=Llama 3.2 1...
2026.03
46
SVDSoftmax
Base Model=Llama 3.2 1...
2026.03
26
Feedback
Search any
task
Search any
task
