Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on MATH500 (Accuracy, Friedman Rank, P(EDEN > competitor))
Loading...
32.8
Accuracy
EDEN
22.608
25.254
27.9
30.546
May 10, 2026
Accuracy
Friedman Rank
P(EDEN > competitor)
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
Friedman Rank
P(EDEN > competitor)
EDEN
total number of branch...
2026.05
32.8
1.25
75
Majority-n
n=5
2026.05
30.8
6.25
99
Diverse Beam Search
beam width=3, total nu...
2026.05
30
4.75
96
Beam Search
beam width=3, total nu...
2026.05
29.2
2.25
78
Best-of-n
n=5
2026.05
28.2
4.62
96
Min-p Sampling
2026.05
28
8
100
Greedy
2026.05
27.4
6.12
99
Top-p Sampling
2026.05
27.4
6.62
99
Top-H Sampling
2026.05
26
8.12
100
Top-k Sampling
2026.05
23
7
100
Feedback
Search any
task
Search any
task