List your company

Code Generation on BigCodeBench (avg@32)

52.46avg@32Code-A1
28.415234.657640.947.1424Mar 16, 2026

Evaluation results

MethodLinks
Code-A1Code LLM=Qwen2.5-Coder-7B-Instruct2026.0352.46
Golden TestsCode LLM=Qwen2.5-Coder-7B-Instruct2026.0352.28
Self-PlayCode LLM=Qwen2.5-Coder-7B-Instruct2026.0352.25
/Code LLM=Qwen2.5-Coder-7B-Instruct2026.0349.41
Code-A1Code LLM=Qwen2.5-Coder-3B-Instruct2026.0345.85
Golden TestsCode LLM=Qwen2.5-Coder-3B-Instruct2026.0345.41
Self-PlayCode LLM=Qwen2.5-Coder-3B-Instruct2026.0345.09
/Code LLM=Qwen2.5-Coder-3B-Instruct2026.0341.78
Code-A1Code LLM=Qwen2.5-Coder-1.5B-Instruct2026.0334.82
Golden TestsCode LLM=Qwen2.5-Coder-1.5B-Instruct2026.0334.23
Self-PlayCode LLM=Qwen2.5-Coder-1.5B-Instruct2026.0333.47
/Code LLM=Qwen2.5-Coder-1.5B-Instruct2026.0329.34