Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on HumanEval (Pass@1 and Pass@10)
Loading...
62
Pass@1
EXPERT
50.352
53.376
56.4
59.424
Apr 1, 2026
Pass@1
Pass@10
Updated 16d ago
Evaluation Results
Method
Method
Links
Pass@1
Pass@10
EXPERT
Base Model=OLMo-3-7B,...
2026.04
62
85.3
TSV
Base Model=OLMo-3-7B,...
2026.04
59
82.4
ACTMat
Base Model=OLMo-3-7B,...
2026.04
58.2
83.7
TA
Base Model=OLMo-3-7B,...
2026.04
57.2
85.1
AVERAGE
Base Model=OLMo-3-7B,...
2026.04
56.8
85.1
ISO-C
Base Model=OLMo-3-7B,...
2026.04
55.9
84.8
REGMEAN
Base Model=OLMo-3-7B,...
2026.04
55.3
81.1
ZERO-SHOT
Base Model=OLMo-3-7B,...
2026.04
50.8
82.2
Feedback
Search any
task
Search any
task