Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on HumanEval (HumanEval, AvgCode, Avg)
Loading...
63.41
HumanEval Score
DoReMi
54.5388
56.8419
59.145
61.4481
Jul 1, 2026
HumanEval Score
AvgCode Score
Average Score
Updated 24d ago
Evaluation Results
Method
Method
Links
HumanEval Score
AvgCode Score
Average Score
DoReMi
Backbone=Qwen3-4B, Dat...
2026.07
63.41
58.61
62
ODM
Backbone=Qwen3-4B, Dat...
2026.07
63.41
52.81
58.77
Grid
Backbone=Qwen3-4B, Dat...
2026.07
62.8
55.2
64.74
CAUSALMIX
Backbone=Qwen3-4B, Dat...
2026.07
62.2
58.6
66.66
RegMix
Backbone=Qwen3-4B, Dat...
2026.07
61.59
57.6
61.4
Equal
Backbone=Qwen3-4B, Dat...
2026.07
59.76
53.98
63.8
DMO
Backbone=Qwen3-4B, Dat...
2026.07
54.88
54.94
63.47
Feedback
Search any
task
Search any
task