Visual Table Question Answering on Visual-TableQA (test)
85.72Relaxed AccuracyGemini 2.5 Flash
Evaluation results
| Method | Links | |
|---|---|---|
| Gemini 2.5 FlashModel Category=Proprietary VLMs, Evaluation Source=LLM jury2025.09 | 85.72 | |
| Qwen2.5-VL-7B-Instruct + Visual-TableQAModel Category=Finetuned VLMs, Evaluation Source=LLM jury2025.09 | 82.98 | |
| Claude 3.5 SonnetModel Category=Proprietary VLMs, Evaluation Source=LLM jury2025.09 | 82.46 | |
| Llama 4 Maverick 17B-128E InstructModel Category=Open-Source VLMs, Evaluation Source=LLM jury2025.09 | 80.75 | |
| Qwen2.5-VL-32B-InstructModel Category=Open-Source VLMs, Evaluation Source=LLM jury2025.09 | 80.45 | |
| Gemini 2.5 ProModel Category=Proprietary VLMs, Evaluation Source=LLM jury2025.09 | 78.62 | |
| GPT-4oModel Category=Proprietary VLMs, Evaluation Source=LLM jury2025.09 | 78.5 | |
| Mistral Small 3.1 24B InstructModel Category=Open-Source VLMs, Evaluation Source=LLM jury2025.09 | 73.2 | |
| Qwen2.5-VL-7B-InstructModel Category=Open-Source VLMs, Evaluation Source=LLM jury2025.09 | 71.35 | |
| GPT-4o miniModel Category=Proprietary VLMs, Evaluation Source=LLM jury2025.09 | 67 | |
| Qwen2.5-VL-7B-Instruct + ReachQAModel Category=Finetuned VLMs, Evaluation Source=LLM jury2025.09 | 60.68 |