Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Code Generation on HumanEval+ (avg@32)
Loading...
85.21
Average Pass Rate @32
Code-A1
62.5484
68.4317
74.315
80.1983
Mar 16, 2026
Average Pass Rate @32
Updated 1mo ago
Evaluation Results
Method
Method
Links
Average Pass Rate @32
Code-A1
Code LLM=Qwen2.5-Coder...
2026.03
85.21
Self-Play
Code LLM=Qwen2.5-Coder...
2026.03
84.7
Golden Tests
Code LLM=Qwen2.5-Coder...
2026.03
84.68
/
Code LLM=Qwen2.5-Coder...
2026.03
83.69
Code-A1
Code LLM=Qwen2.5-Coder...
2026.03
83.52
Golden Tests
Code LLM=Qwen2.5-Coder...
2026.03
81.96
Self-Play
Code LLM=Qwen2.5-Coder...
2026.03
81.86
/
Code LLM=Qwen2.5-Coder...
2026.03
77.63
Code-A1
Code LLM=Qwen2.5-Coder...
2026.03
72.69
Golden Tests
Code LLM=Qwen2.5-Coder...
2026.03
71.15
Self-Play
Code LLM=Qwen2.5-Coder...
2026.03
70.64
/
Code LLM=Qwen2.5-Coder...
2026.03
63.42
Feedback
Search any
task
Search any
task