Chart-to-code generation on ChartMimic Chart2Python (test)
48.5Error RateInternVL3.5-2B
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| InternVL3.5-2BModel Category=Open-source2026.04 | 48.5 | 65.6 | 32.5 | 31.3 | |
| DeepSeek-VL2-3BModel Category=Open-source2026.04 | 50.2 | 69.4 | 35 | 35 | |
| ChartMoE-8BModel Category=Open-source2026.04 | 52.7 | 56.9 | 22.9 | 25.3 | |
| Qwen3-VL-2BModel Category=Open-source2026.04 | 56.3 | 68.4 | 39.7 | 39.2 | |
| ChartLlama-13BModel Category=Open-source2026.04 | 57.5 | 44.9 | 28.1 | 24.8 | |
| LLaVA-v1.6-7BModel Category=Open-source2026.04 | 62 | 55.9 | 25.7 | 25.9 | |
| InternVL3.5-4BModel Category=Open-source2026.04 | 62.8 | 69.5 | 44.7 | 43 | |
| ChartLlama-13BModel Category=Open-source2026.04 | 65.3 | 46 | 14.8 | 16.2 | |
| Phi-3.5-vision-4BModel Category=Open-source2026.04 | 66.7 | 44.1 | 41 | 38.6 | |
| Phi-3.5-vision-4BModel Category=Open-source2026.04 | 68.8 | 53.3 | 56.1 | 34.2 | |
| ChartMoE-8BModel Category=Open-source2026.04 | 69.5 | 64.2 | 40.2 | 35.4 | |
| InternVL3.5-2BModel Category=Open-source2026.04 | 69.8 | 76.1 | 53.2 | 53.1 | |
| LLaVA-v1.6-7BModel Category=Open-source2026.04 | 71 | 65.7 | 38 | 39.5 | |
| InternVL3.5-8BModel Category=Open-source2026.04 | 71.2 | 71 | 52.1 | 48.9 | |
| DeepSeek-VL2-3BModel Category=Open-source2026.04 | 72 | 80.2 | 58.7 | 58 | |
| Qwen3-VL-4BModel Category=Open-source2026.04 | 72.5 | 71.9 | 58.4 | 55.2 | |
| Qwen3-VL-2BModel Category=Open-source2026.04 | 74 | 78 | 59.6 | 61 | |
| InternVL3.5-4BModel Category=Open-source2026.04 | 77.9 | 78.4 | 63.4 | 63 | |
| Qwen3-VL-8BModel Category=Open-source2026.04 | 78.7 | 72.5 | 65.2 | 61.9 | |
| InternVL3.5-8BModel Category=Open-source2026.04 | 82.5 | 79.6 | 67.5 | 67 | |
| CharLuMA-1.3BModel Category=Open-source2026.04 | 83 | 71.8 | 64.8 | 62.5 | |
| GPT-5-miniModel Category=Proprietary2026.04 | 85.2 | 89 | 80 | 67.5 | |
| GPT-5-miniModel Category=Proprietary2026.04 | 86.8 | 86.9 | 78.2 | 71.5 | |
| Qwen3-VL-4BModel Category=Open-source2026.04 | 87.6 | 83.2 | 77.2 | 76.1 | |
| Claude-Haiku-3.5Model Category=Proprietary2026.04 | 88 | 76.2 | 73.5 | 65.7 | |
| GPT-4o-miniModel Category=Proprietary2026.04 | 89 | 77.5 | 74.8 | 70.2 | |
| Qwen3-VL-8BModel Category=Open-source2026.04 | 91.1 | 83.7 | 80.8 | 80.6 | |
| Claude-Haiku-3.5Model Category=Proprietary2026.04 | 91.3 | 81.6 | 76.7 | 68.8 | |
| ChartCoder-7BModel Category=Open-source2026.04 | 91.4 | 69.2 | 74 | 72.5 | |
| CharLuMA-6.7BModel Category=Open-source2026.04 | 92.3 | 77.4 | 75.1 | 73.3 | |
| GPT-4oModel Category=Proprietary2026.04 | 93.2 | 83.5 | 83.5 | 79 | |
| CharLuMA-1.3BModel Category=Open-source2026.04 | 94.4 | 86.5 | 78.4 | 76.9 | |
| GPT-4o-miniModel Category=Proprietary2026.04 | 94.8 | 81.2 | 79.8 | 74.5 | |
| Claude-Sonnet-4Model Category=Proprietary2026.04 | 96.2 | 83.3 | 86.4 | 81.5 | |
| ChartCoder-7BModel Category=Open-source2026.04 | 96.2 | 48.1 | 86.4 | 56.1 | |
| CharLuMA-6.7BModel Category=Open-source2026.04 | 98 | 88.7 | 88.1 | 83.5 | |
| Claude-Sonnet-4Model Category=Proprietary2026.04 | 98.3 | 86.8 | 88 | 81.4 | |
| GPT-4oModel Category=Proprietary2026.04 | 98.5 | 85 | 87.4 | 80.9 |