Multimodal code generation on PandasPlotBench
85.1Execution RatePairCoder
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PairCoderBase Model=gpt-5.4-mini, Reasoning Status=thinking off, Collaboration Framework=PairCoder2026.07 | 85.1 | 46.1 | 79.4 | |
| gpt-5.4-miniBase Model=gpt-5.4-mini, Reasoning Status=thinking off, Collaboration Framework=single2026.07 | 78.9 | 42.3 | 72.8 |