Vision Question Answering on Q-Bench LLVisionQA 1.0 (dev)
74.5Overall ScorePhotoEye
Evaluation Results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| PhotoEyeLLM Backbone=Vicuna-v1.5-7B2025.09 | 74.5 | 80.01 | 76.1 | 67.02 | 74.32 | 74.59 | |
| IQA-SpiderBackbone=Qwen3-VL2026.05 | 74.45 | — | — | — | — | — | |
| Qwen-VL-MaxLLM Backbone=Proprietary Model2025.09 | 73.63 | 75.6 | 79.43 | 66.09 | 73.39 | 74.08 | |
| IQA-SpiderBackbone=Qwen2.5-VL2026.05 | 73.24 | — | — | — | — | — | |
| GPT-4o (2024-08-06)LLM Backbone=Proprietary Model2025.09 | 73.04 | 76.72 | 74.33 | 67.74 | 70.03 | 73.37 | |
| IQA-SpiderBackbone=Phi-3.5-Vision2026.05 | 70.3 | — | — | — | — | — | |
| SPHINXLLM Backbone=LLaMA-22025.09 | 68.56 | 74.18 | 68.81 | 62.07 | 63.62 | 71.76 | |
| Gemini-ProLLM Backbone=Proprietary Model2025.09 | 68.16 | 68.8 | 73.74 | 62.34 | 66.3 | 71.34 | |
| Q-Instruct2026.05 | 67.56 | — | — | — | — | — | |
| Q-InstructLLM Backbone=Vicuna-v1.5-7B2025.09 | 67.09 | 76.18 | 66.37 | 57.61 | 65.18 | 67.59 | |
| Qwen-VL-PlusLLM Backbone=Proprietary Model2025.09 | 66.04 | 73.77 | 69.47 | 53.88 | 66.21 | 65.72 | |
| InternLM-XComposer-VLLLM Backbone=InternLM2025.09 | 65.35 | 69.45 | 65.27 | 60.85 | 61.67 | 70.14 | |
| InternLM-XComposer-VL2026.05 | 65.35 | — | — | — | — | — | |
| Emu2-ChatLLM Backbone=LLaMA-2-33B2025.09 | 65.28 | 71.81 | 67.25 | 56.18 | 64.78 | 63.19 | |
| AesExpertLLM Backbone=Vicuna-v1.5-7B2025.09 | 64.15 | 73.27 | 64.38 | 53.75 | 70.03 | 73.38 | |
| LLaVA-v1.5(13B)Parameters=13B2026.05 | 62.14 | — | — | — | — | — | |
| mPLUG-Owl2LLM Backbone=LLaMA-2-7B2025.09 | 61.61 | 72.18 | 57.96 | 56.19 | 56.68 | 69.21 | |
| mPLUG-Owl22026.05 | 61.61 | — | — | — | — | — | |
| LLAMA-Adapter-V2LLM Backbone=LLaMA-2-7B2025.09 | 59.46 | 66.18 | 59.29 | 52.13 | 57.39 | 56.25 | |
| Qwen-VLLLM Backbone=QwenLM2025.09 | 59.4 | 63.09 | 58.19 | 56.39 | 50.58 | 62.73 | |
| LLAVA-v1.5LLM Backbone=Vicuna-v1.5-7B2025.09 | 58.66 | 66.36 | 58.19 | 50.51 | 49.42 | 65.74 | |
| LLaVA-v1.5(7B)Parameters=7B2026.05 | 58.66 | — | — | — | — | — | |
| InstructBLIPLLM Backbone=Vicuna-v1.5-7B2025.09 | 56.72 | 71.64 | 52.65 | 43.81 | 48.64 | 62.5 | |
| ShikraLLM Backbone=Vicuna-v1.5-7B2025.09 | 54.65 | 65.64 | 47.35 | 49.09 | 48.83 | 59.49 | |
| MiniGPT-4LLM Backbone=Vicuna-v1.5-13B2025.09 | 49.03 | 55.82 | 50.22 | 40.37 | 42.02 | 48.38 | |
| IDEFICS-InstructLLM Backbone=LLaMA-2-7B2025.09 | 48.7 | 56.18 | 44.69 | 44.02 | 42.8 | 54.17 | |
| Otter-v1LLM Backbone=MPT-7B2025.09 | 46.35 | 57.09 | 40.71 | 39.55 | 42.22 | 49.31 | |
| Random guessLLM Backbone=-2025.09 | 37.8 | 50 | 27.86 | 33.31 | 37.89 | 38.48 | |
| random guess2026.05 | 37.8 | — | — | — | — | — |