Multi-modal Understanding on MMMU (Accuracy)
49.1AccuracyViQ
Evaluation Results
| Method | Links | |
|---|---|---|
| ViQBase LLM=Qwen2.5-7B, Size=1.3B, AnyRes=true, Discrete=true2026.06 | 49.1 | |
| ViQBase LLM=Qwen2.5 - 7B, Size=1.3B, AnyRes=true, Discrete=true2026.06 | 49.1 | |
| SigLIP2-gBase LLM=Qwen2.5-7B, Size=1.1B, AnyRes=false, Discrete=false2026.06 | 48.3 | |
| SigLIP2-gBase LLM=Qwen2.5 - 7B, Size=1.1B, AnyRes=false, Discrete=false2026.06 | 48.3 | |
| AIMv2-HBase LLM=Qwen2.5-7B, Size=0.7B, AnyRes=false, Discrete=false2026.06 | 48.2 | |
| AIMv2-HBase LLM=Qwen2.5 - 7B, Size=0.7B, AnyRes=false, Discrete=false2026.06 | 48.2 | |
| OryxViTBase LLM=Qwen2.5-7B, Size=0.4B, AnyRes=true, Discrete=false2026.06 | 48.1 | |
| InternViT-2.5-6BBase LLM=Qwen2.5-7B, Size=6.0B, AnyRes=false, Discrete=false2026.06 | 48.1 | |
| OryxViTBase LLM=Qwen2.5 - 7B, Size=0.4B, AnyRes=true, Discrete=false2026.06 | 48.1 | |
| InternViT-2.5-6BBase LLM=Qwen2.5 - 7B, Size=6.0B, AnyRes=false, Discrete=false2026.06 | 48.1 | |
| OAI-CLIP-LBase LLM=Qwen2.5-7B, Size=0.3B, AnyRes=false, Discrete=false2026.06 | 47.1 | |
| OAI-CLIP-LBase LLM=Qwen2.5 - 7B, Size=0.3B, AnyRes=false, Discrete=false2026.06 | 47.1 | |
| ViQBase LLM=Qwen2.5-1.5B, Size=1.3B, AnyRes=true, Discrete=true2026.06 | 42.6 | |
| ViQBase LLM=Qwen2.5 - 1.5B, Size=1.3B, AnyRes=true, Discrete=true2026.06 | 42.6 | |
| SigLIP2-gBase LLM=Qwen2.5-1.5B, Size=1.1B, AnyRes=false, Discrete=false2026.06 | 42.4 | |
| SigLIP2-gBase LLM=Qwen2.5 - 1.5B, Size=1.1B, AnyRes=false, Discrete=false2026.06 | 42.4 | |
| OryxViTBase LLM=Qwen2.5-1.5B, Size=0.4B, AnyRes=true, Discrete=false2026.06 | 42.1 | |
| InternViT-2.5-6BBase LLM=Qwen2.5-1.5B, Size=6.0B, AnyRes=false, Discrete=false2026.06 | 42.1 | |
| OryxViTBase LLM=Qwen2.5 - 1.5B, Size=0.4B, AnyRes=true, Discrete=false2026.06 | 42.1 | |
| InternViT-2.5-6BBase LLM=Qwen2.5 - 1.5B, Size=6.0B, AnyRes=false, Discrete=false2026.06 | 42.1 | |
| DinoV2-gBase LLM=Qwen2.5-1.5B, Size=1.1B, AnyRes=false, Discrete=false2026.06 | 41.8 | |
| AIMv2-HBase LLM=Qwen2.5-1.5B, Size=0.7B, AnyRes=false, Discrete=false2026.06 | 41.8 | |
| DinoV2-gBase LLM=Qwen2.5 - 1.5B, Size=1.1B, AnyRes=false, Discrete=false2026.06 | 41.8 | |
| AIMv2-HBase LLM=Qwen2.5 - 1.5B, Size=0.7B, AnyRes=false, Discrete=false2026.06 | 41.8 | |
| OAI-CLIP-LBase LLM=Qwen2.5-1.5B, Size=0.3B, AnyRes=false, Discrete=false2026.06 | 40.7 | |
| OAI-CLIP-LBase LLM=Qwen2.5 - 1.5B, Size=0.3B, AnyRes=false, Discrete=false2026.06 | 40.7 | |
| InternViT-2.5Base LLM=Qwen2.5-1.5B, Size=0.3B, AnyRes=false, Discrete=false2026.06 | 40.3 | |
| InternViT-2.5Base LLM=Qwen2.5 - 1.5B, Size=0.3B, AnyRes=false, Discrete=false2026.06 | 40.3 | |
| QLIPBase LLM=Qwen2.5-1.5B, Size=0.3B, AnyRes=false, Discrete=true2026.06 | 36.9 | |
| QLIPBase LLM=Qwen2.5 - 1.5B, Size=0.3B, AnyRes=false, Discrete=true2026.06 | 36.9 | |
| UniTokBase LLM=Qwen2.5-1.5B, Size=0.3B, AnyRes=false, Discrete=true2026.06 | 36.1 | |
| UniTokBase LLM=Qwen2.5 - 1.5B, Size=0.3B, AnyRes=false, Discrete=true2026.06 | 36.1 | |
| MolmoE-1B-7BAvg_k=8.002026.06 | 31.2 | |
| GeMoEAvg_k=5.432026.06 | 30.5 |