Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Problem Solving on MMLU STEM
Loading...
63.9
Accuracy
Minerva
34.468
42.109
49.75
57.391
Feb 5, 2024
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Minerva
Size=540B, Evaluation=...
2024.02
63.9
DeepSeekMath-Base
Size=7B, Evaluation=Ch...
2024.02
56.5
Minerva
Size=62B, Evaluation=C...
2024.02
53.9
Llemma
Size=34B, Evaluation=C...
2024.02
52.9
Mistral
Size=7B, Evaluation=Ch...
2024.02
51.1
Llemma
Size=7B, Evaluation=Ch...
2024.02
43.1
Minerva
Size=7B, Evaluation=Ch...
2024.02
35.6
Feedback
Search any
task
Search any
task
