Vision-Language Evaluation on MME Leaderboard (full)
138.33Existence ScoreHALC
Evaluation Results
| Method | Links | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| HALCModel=MiniGPT-4, Tokens=128, Samples=1202025.05 | 138.33 | — | — | — | — | — | 63.33 | 58.33 | 78.33 | — | — | — | — | — | — | — | |
| RVCDModel=MiniGPT-4, Tokens=128, Samples=1202025.05 | 130 | — | — | — | — | — | 51.66 | 53.33 | 70 | — | — | — | — | — | — | — | |
| RVCDModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05 | 130 | — | — | — | — | — | 70 | 53.33 | 125 | — | — | — | — | — | — | — | |
| DoLaModel=MiniGPT-4, Tokens=128, Samples=1202025.05 | 128.33 | — | — | — | — | — | 60 | 60 | 78.33 | — | — | — | — | — | — | — | |
| VCDModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05 | 126.66 | — | — | — | — | — | 81.66 | 55 | 91.66 | — | — | — | — | — | — | — | |
| VCDModel=MiniGPT-4, Tokens=128, Samples=1202025.05 | 125 | — | — | — | — | — | 53.33 | 51.66 | 65 | — | — | — | — | — | — | — | |
| RVCDModel=LLaVA-1.5, Tokens=128, Samples=1202025.05 | 123.33 | — | — | — | — | — | 60 | 65 | 95 | — | — | — | — | — | — | — | |
| GreedyModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05 | 111.66 | — | — | — | — | — | 68.33 | 70 | 120 | — | — | — | — | — | — | — | |
| DoLaModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05 | 111.66 | — | — | — | — | — | 65 | 65 | 120 | — | — | — | — | — | — | — | |
| GreedyModel=MiniGPT-4, Tokens=128, Samples=1202025.05 | 108.33 | — | — | — | — | — | 48.33 | 56.66 | 78.33 | — | — | — | — | — | — | — | |
| GreedyModel=LLaVA-1.5, Tokens=128, Samples=1202025.05 | 105 | — | — | — | — | — | 60 | 50 | 65 | — | — | — | — | — | — | — | |
| OperaModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05 | 105 | — | — | — | — | — | 63.33 | 50 | 90 | — | — | — | — | — | — | — | |
| VCDModel=LLaVA-1.5, Tokens=128, Samples=1202025.05 | 100 | — | — | — | — | — | 56.66 | 60 | 85 | — | — | — | — | — | — | — | |
| HALCModel=mPLUG-Owl2, Tokens=128, Samples=1202025.05 | 98.33 | — | — | — | — | — | 65 | 53.33 | 115 | — | — | — | — | — | — | — | |
| OperaModel=LLaVA-1.5, Tokens=128, Samples=1202025.05 | 88.33 | — | — | — | — | — | 60 | 53.33 | 80 | — | — | — | — | — | — | — | |
| DoLaModel=LLaVA-1.5, Tokens=128, Samples=1202025.05 | 75 | — | — | — | — | — | 53.33 | 55 | 60 | — | — | — | — | — | — | — | |
| HALCModel=LLaVA-1.5, Tokens=128, Samples=1202025.05 | 73.33 | — | — | — | — | — | 58.33 | 53.33 | 65 | — | — | — | — | — | — | — | |
| OperaModel=MiniGPT-4, Tokens=128, Samples=1202025.05 | 71.66 | — | — | — | — | — | 46.66 | 56.66 | 53.33 | — | — | — | — | — | — | — |