Multimodal Code Generation on ChartMimic
0.978Execution RateClaude-4.5-Sonnet
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| Claude-4.5-Sonnet2026.01 | 0.978 | 0.896 | 0.829 | |
| Gemini-2.5-Pro2026.01 | 0.973 | 0.887 | 0.838 | |
| GPT-52026.01 | 0.948 | 0.819 | 0.783 | |
| Qwen2.5-VL-72BParameters=72B2026.01 | 0.885 | 0.727 | 0.791 | |
| OCRVerseParameters=4B2026.01 | 0.848 | 0.722 | 0.754 | |
| Qwen3-VL-32BParameters=32B2026.01 | 0.83 | 0.669 | 0.775 | |
| InternVL3.5-38BParameters=38B2026.01 | 0.79 | 0.6 | 0.718 | |
| Qwen3-VL-8BParameters=8B2026.01 | 0.783 | 0.625 | 0.678 | |
| InternVL3.5-14BParameters=14B2026.01 | 0.732 | 0.528 | 0.554 | |
| InternVL3-14BParameters=14B2026.01 | 0.723 | 0.513 | 0.541 | |
| Qwen2.5-VL-7BParameters=7B2026.01 | 0.687 | 0.422 | 0.401 | |
| InternVL3.5-8BParameters=8B2026.01 | 0.667 | 0.46 | 0.483 | |
| InternVL3-8BParameters=8B2026.01 | 0.633 | 0.438 | 0.461 |