Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Benchmarking on MMBench en (dev)
Loading...
63.75
Overall Accuracy
Uni-DPO
42.9292
48.3346
53.74
59.1454
Jun 11, 2025
Overall Accuracy
Updated 8d ago
Evaluation Results
Method
Method
Links
Overall Accuracy
Uni-DPO
Model=Qwen2-VL-2B
2025.06
63.75
SimPO
Model=Qwen2-VL-2B
2025.06
54.38
Baseline
Model=Qwen2-VL-2B
2025.06
50.09
DPO
Model=Qwen2-VL-2B
2025.06
43.73
Feedback
Search any
task
Search any
task
