Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MATH (Accuracy Improvement Delta)
Loading...
10.2
Accuracy Improvement Delta
Ultra-Dense Prompting
8.016
8.583
9.15
9.717
Apr 19, 2026
Accuracy Improvement Delta
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy Improvement Delta
Ultra-Dense Prompting
Model=Gemini 2.0
2026.04
10.2
Ultra-Dense Prompting
Model=Claude 3.7
2026.04
9.4
Ultra-Dense Prompting
Model=Average across M...
2026.04
9.1
Ultra-Dense Prompting
Model=GPT-4o
2026.04
8.8
Ultra-Dense Prompting
Model=GPT-4o-mini
2026.04
8.1
Feedback
Search any
task
Search any
task