Multimodal Evaluation (Cognition/Summary) on MME Summary
1,796.6MME Summary ScoreUniWeTok-Chat
Evaluation results
| Method | Links | |
|---|---|---|
| UniWeTok-ChatPretrained-LLM=Qwen3-8B, Model Category=Unified Model2026.02 | 1,796.6 | |
| LLaVA-1.6(HD)Pretrained-LLM=Vicuna-7B, Model Category=Understanding Only Model2026.02 | 1,778 | |
| TokenFlow-LPretrained-LLM=Vicuna-13B, Model Category=Unified Model2026.02 | 1,622.9 | |
| HarmonPretrained-LLM=Qwen2.5-1.5B, Model Category=Unified Model2026.02 | 1,476 |