List your company

Multimodal code generation on PandasPlotBench

85.1Execution RatePairCoder
78.65280.3268283.674Jul 2, 2026

Evaluation results

MethodLinks
PairCoderBase Model=gpt-5.4-mini, Reasoning Status=thinking off, Collaboration Framework=PairCoder2026.0785.146.179.4
gpt-5.4-miniBase Model=gpt-5.4-mini, Reasoning Status=thinking off, Collaboration Framework=single2026.0778.942.372.8