List your company

Text-to-Code Generation on PandasPlotBench

9.7Code Error RateJANUSCODER-14B
9.01213.65618.322.944Oct 27, 2025

Evaluation results

MethodLinks
JANUSCODER-14BModel Type=Open-Source, Parameters=14B2025.109.767
GPT-4oModel Type=Proprietary2025.109.772
Qwen2.5-Coder-32B-InsModel Type=Open-Source, Parameters=32B2025.101266
Qwen3-14BModel Type=Open-Source, Parameters=14B2025.1012.665
JANUSCODER-8BModel Type=Open-Source, Parameters=8B2025.1014.963
Qwen3-8BModel Type=Open-Source, Parameters=8B2025.102063
Qwen2.5-Coder-7B-InsModel Type=Open-Source, Parameters=7B2025.1021.163
LLaMA3-8B-InstructModel Type=Open-Source, Parameters=8B2025.1026.959