Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multiple Choice Question Answering on Long-form Multiple Choice Question Answering benchmark
Loading...
83.2
Accuracy
Qwen2.5-VL
60.944
66.722
72.5
78.278
Mar 26, 2026
Accuracy
Updated 22d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-VL
Training Paradigm=Rank
2026.03
83.2
Qwen2.5-VL
Training Paradigm=DPO
2026.03
82.6
Qwen2.5-VL
Training Paradigm=MPO
2026.03
82.5
Qwen2.5-VL
Training Paradigm=Pret...
2026.03
82
Qwen2.5-VL
Training Paradigm=SFT
2026.03
81.9
PerceptionLM
Training Paradigm=DPO
2026.03
64.4
PerceptionLM
Training Paradigm=Rank
2026.03
64.4
PerceptionLM
Training Paradigm=MPO
2026.03
64.2
PerceptionLM
Training Paradigm=SFT
2026.03
61.9
PerceptionLM
Training Paradigm=Pret...
2026.03
61.8
Feedback
Search any
task
Search any
task