Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Large Multimodal Model Evaluation on MLLM-as-a-Judge v1.0 (test)

49Overall Score

GPT-4V

13.74422.89732.0541.203Oct 3, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.10
4963.677.3
2024.10
43.957.773.6
2024.10
42.453.871.7
39.357.871.5
31.455.668.9
2024.10
31.254.667.5
2024.10
30.450.961.5
28.751.370.1
2024.10
27.254.767.7
25.334.864.5
2024.10
23.752.965.8
2024.10
22.852.865.6
2024.10
21.3--
2024.10
19.846.158.6
15.843.957.6
15.142.655