Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Proof Optimization (Length) on Mathlib
Loading...
6.19
Improvement
ImProver
-0.2476
1.4237
3.095
4.7663
Oct 7, 2024
Improvement
Nonempty Improvement
Accuracy
Improved Accuracy
Updated 12d ago
Evaluation Results
Method
Method
Links
Improvement
Nonempty Improvement
Accuracy
Improved Accuracy
ImProver
Model=ImProver
2024.10
6.19
53.65
100
11.54
ImProver
Model=ImProver
2024.10
4.16
7.45
100
9.3
GPT-4o
Model=GPT-4o
2024.10
2.92
30.14
9.3
4.65
GPT-4o
Model=GPT-4o
2024.10
0
0
16.67
0
Feedback
Search any
task
Search any
task