Chart-to-code generation on Plot2Code Chart2Python (test)
61.4Error Rate (ER)InternVL3.5-2B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| InternVL3.5-2BModel Category=Open-source2026.04 | 61.4 | 55.7 | 34.2 | 44.2 | |
| InternVL3.5-4BModel Category=Open-source2026.04 | 62.1 | 58.8 | 38 | 42.7 | |
| Qwen3-VL-2BModel Category=Open-source2026.04 | 68.9 | 64.2 | 41.2 | 50.1 | |
| LLaVA-v1.6-7BModel Category=Open-source2026.04 | 69.7 | 49.8 | 26.5 | 32.5 | |
| ChartMoE-8BModel Category=Open-source2026.04 | 70.5 | 58.9 | 37.6 | 26.9 | |
| DeepSeek-VL2-3BModel Category=Open-source2026.04 | 72.5 | 59.8 | 45.4 | 44.2 | |
| Phi-3.5-vision-4BModel Category=Open-source2026.04 | 72.7 | 63.8 | 43.1 | 42.6 | |
| InternVL3.5-8BModel Category=Open-source2026.04 | 74.2 | 61 | 47.2 | 49.1 | |
| Qwen3-VL-4BModel Category=Open-source2026.04 | 77.3 | 66.4 | 54.4 | 55.4 | |
| Qwen3-VL-8BModel Category=Open-source2026.04 | 78.8 | 68.1 | 57.3 | 56.9 | |
| ChartLlama-13BModel Category=Open-source2026.04 | 81.8 | 50.1 | 18.9 | 22.4 | |
| CharLuMA-1.3BModel Category=Open-source2026.04 | 83.3 | 64.3 | 50.6 | 47.2 | |
| Claude-Haiku-3.5Model Category=Proprietary2026.04 | 87.1 | 72.8 | 60.6 | 56.8 | |
| ChartCoder-7BModel Category=Open-source2026.04 | 87.9 | 65.7 | 58.2 | 56.6 | |
| GPT-4o-miniModel Category=Proprietary2026.04 | 90.2 | 77.8 | 63.8 | 67 | |
| GPT-4oModel Category=Proprietary2026.04 | 92.4 | 83.6 | 76.7 | 75.4 | |
| GPT-5-miniModel Category=Proprietary2026.04 | 93.2 | 85.9 | 72.7 | 72.8 | |
| Claude-Sonnet-4Model Category=Proprietary2026.04 | 95.5 | 81.2 | 81 | 76.8 | |
| CharLuMA-6.7BModel Category=Open-source2026.04 | 96.2 | 68.3 | 62.2 | 60.5 |