Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-discipline Multimodal Understanding and Reasoning on MMMU
Loading...
42.8
Overall Score
Qwen2-VL-2B-Instruct (DPO, Full)
41.032
41.491
41.95
42.409
May 29, 2025
Overall Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Overall Score
Qwen2-VL-2B-Instruct (DPO, Full)
% Train=100, Train set...
2025.05
42.8
Qwen2-VL-2B-Instruct (DPO, HighAvg.)
% Train=33, Train set=...
2025.05
42.6
Qwen2-VL-2B-Instruct (DPO, LowAvg.)
% Train=33, Train set=...
2025.05
42.2
Qwen2-VL-2B-Instruct (DPO, HighVar.)
% Train=33, Train set=...
2025.05
42.1
Qwen2-VL-2B-Instruct (DPO, Random)
% Train=33, Train set=...
2025.05
42
Qwen2-VL-2B-Instruct (Zeroshot)
% Train=0, Train set=Z...
2025.05
41.1
Feedback
Search any
task
Search any
task