Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Visual Question Answering on SLAKE
Loading...
32.62
Accuracy
SPINE
8.1072
14.4711
20.835
27.1989
Nov 22, 2025
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
SPINE
Base Model=Qwen2.5-VL-...
2025.11
32.62
TTRL
Base Model=Qwen2.5-VL-...
2025.11
30
No adaptation
Base Model=Qwen2.5-VL-...
2025.11
26.17
Self-Consistency
Base Model=Qwen2.5-VL-...
2025.11
25.84
SEALONG
Base Model=Qwen2.5-VL-...
2025.11
12.32
LMSI
Base Model=Qwen2.5-VL-...
2025.11
9.05
Feedback
Search any
task
Search any
task