Visual Perception on MME
1,726.77Perception ScoreSelf-Aug
Evaluation results
| Method | Links | |
|---|---|---|
| Self-AugModel=Qwen3-VL-8B2025.10 | 1,726.77 | |
| MultinomialModel=Qwen3-VL-8B2025.10 | 1,725.16 | |
| VACoDeModel=Qwen3-VL-8B2025.10 | 1,722.62 | |
| InternLM-XComposer2LLM=InternLM2-7B2024.01 | 1,712 | |
| VCDModel=Qwen3-VL-8B2025.10 | 1,704.11 | |
| ShareGPT4VLLM=Vicuna-7B2024.01 | 1,567.4 | |
| LLaVA-1.5LLM=Vicuna-13B2024.01 | 1,531.3 | |
| InternLM-XCLLM=InternLM-7B2024.01 | 1,528.4 | |
| Monkey-10BLLM=Qwen-7B2024.01 | 1,522.4 | |
| Qwen-VL-ChatLLM=Qwen-7B2024.01 | 1,487.5 | |
| Self-AugModel=LLaVA-1.5-13B2025.10 | 1,462.18 | |
| Self-AugModel=Qwen-VL2025.10 | 1,442.36 | |
| VACoDeModel=LLaVA-1.5-13B2025.10 | 1,434.09 | |
| Self-AugModel=LLaVA-1.5-7B2025.10 | 1,431.3 | |
| VCDModel=Qwen-VL2025.10 | 1,415.12 | |
| VACoDeModel=Qwen-VL2025.10 | 1,412.43 | |
| VCDModel=LLaVA-1.5-13B2025.10 | 1,372.77 | |
| VACoDeModel=LLaVA-1.5-7B2025.10 | 1,372.5 | |
| MultinomialModel=LLaVA-1.5-13B2025.10 | 1,351.69 | |
| VCDModel=LLaVA-1.5-7B2025.10 | 1,323.67 | |
| MultinomialModel=Qwen-VL2025.10 | 1,311.79 | |
| BLIP-2LLM=FLAN-T52024.01 | 1,293.8 | |
| MultinomialModel=LLaVA-1.5-7B2025.10 | 1,278.42 | |
| Self-AugModel=InstructBLIP2025.10 | 1,198.53 | |
| VACoDeModel=InstructBLIP2025.10 | 1,090.88 | |
| VCDModel=InstructBLIP2025.10 | 1,079.39 | |
| MultinomialModel=InstructBLIP2025.10 | 973.66 | |
| LLaVALLM=Vicuna-7B2024.01 | 807 |