Multimodal code generation on Plot2Code (execution rate, SSIM, CLIP)
0.962Execution RatePairCoder
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| PairCoderBase Model=gpt-5.4-mini, Reasoning Status=thinking off, Collaboration Framework=PairCoder2026.07 | 0.962 | 47.4 | 91.2 | |
| gpt-5.4-miniBase Model=gpt-5.4-mini, Reasoning Status=thinking off, Collaboration Framework=single2026.07 | 0.841 | 41.2 | 80.2 |