Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on HumanEval (Accuracy, Friedman Rank, P(EDEN > competitor))
Loading...
31.3
Accuracy
EDEN
19.132
22.291
25.45
28.609
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
31.3
1.25
0.75
Beam Search
beam width=3, total nu...
2026.05
28.8
2.25
0.78
Top-k Sampling
2026.05
27.6
7
1
Greedy
2026.05
27
6.12
0.99
Top-p Sampling
2026.05
27
6.62
0.99
Top-H Sampling
2026.05
27
8.12
1
Best-of-n
n=5
2026.05
27
4.62
0.96
Diverse Beam Search
beam width=3, total nu...
2026.05
26.4
4.75
0.96
Min-p Sampling
2026.05
25.8
8
1
Majority-n
n=5
2026.05
19.6
6.25
0.99
Feedback
Search any
task
Search any
task