Chart Question Answering on ChartQA Human-authored
69.36L-AccuracyGemini-2.0-flash
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Gemini-2.0-flashPrompting=CoT2026.04 | 69.36 | — | |
| Gemini-2.0-flashPrompting=Zero-shot2026.04 | 68.02 | — | |
| Claude-3.7-SonnetPrompting=CoT2026.04 | 66.47 | — | |
| Claude-3.7-SonnetPrompting=Zero-shot2026.04 | 65.7 | — | |
| GPT-4.1Prompting=CoT2026.04 | 59.54 | — | |
| GPT-4.1Prompting=Zero-shot2026.04 | 58.96 | — | |
| Pixtral-12BPrompting=CoT2026.04 | 53.37 | — | |
| Pixtral-12BPrompting=Zero-shot2026.04 | 50.67 | — | |
| Gemma-3-4b-itPrompting=CoT2026.04 | 21.58 | — | |
| Gemma-3-4b-itPrompting=Zero-shot2026.04 | 20.62 | — | |
| ChartGemmaPrompting=CoT2026.04 | 19.11 | — | |
| ChartGemmaPrompting=Zero-shot2026.04 | 18.11 | — | |
| LLaMA-3.2-11B-VisionPrompting=Zero-shot2026.04 | 17.15 | — | |
| LLaVA1.5-7bPrompting=CoT2026.04 | 11.95 | — | |
| LLaVA1.5-7bPrompting=Zero-shot2026.04 | 11.56 | — | |
| LLaMA-3.2-11B-VisionPrompting=CoT2026.04 | 8.48 | — | |
| MatChaPrompting=Zero-shot2026.04 | 8.29 | — | |
| MatChaPrompting=CoT2026.04 | 6.17 | — | |
| ChartAgentbackbone=Qwen3VL-30b2025.12 | — | 75.23 | |
| ChartAgentbackbone=Qwen3VL-235b2025.12 | — | 83.3 | |
| ChartGemmacategory=Chart Model2025.12 | — | 80.16 | |
| ChartInstructcategory=Chart Model2025.12 | — | 66.64 | |
| ChartLlamacategory=Chart Model2025.12 | — | 58.4 | |
| ChartMoEcategory=Chart Model2025.12 | — | 78.32 | |
| ChartVLMcategory=Chart Model2025.12 | — | 42.08 | |
| Claude4category=General MLLM2025.12 | — | 76.16 | |
| Gemini-2.5category=General MLLM2025.12 | — | 78.23 | |
| GPT-4ocategory=General MLLM2025.12 | — | 69.52 | |
| MatChacategory=Chart Model2025.12 | — | 37.12 | |
| Qwen2.5VL-72bcategory=General MLLM2025.12 | — | 62.95 | |
| Qwen3VL-235bcategory=General MLLM2025.12 | — | 77.36 | |
| Qwen3VL-30bcategory=General MLLM2025.12 | — | 66.18 | |
| TinyChartcategory=Chart Model2025.12 | — | 58.72 | |
| UniChartcategory=Chart Model2025.12 | — | 34.64 |