Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Utility on ScienceQA
Loading...
61.33
Score
DINM
20.1668
30.8534
41.54
52.2266
Mar 13, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
DINM
Model=LLaVA
2026.03
61.33
Baseline
Model=LLaVA
2026.03
60
Neural Gate
Model=LLaVA
2026.03
60
AlphaEdit
Model=LLaVA
2026.03
59.67
SKU*
Model=LLaVA
2026.03
58.5
MEMIT
Model=LLaVA
2026.03
57.83
Neural Gate
Model=MiniGPT
2026.03
57.5
MemFlex*
Model=LLaVA
2026.03
57.5
Baseline
Model=MiniGPT
2026.03
56.5
AlphaEdit
Model=MiniGPT
2026.03
56
DINM
Model=MiniGPT
2026.03
54.33
SKU*
Model=MiniGPT
2026.03
53.5
MEMIT
Model=MiniGPT
2026.03
52.92
MemFlex*
Model=MiniGPT
2026.03
21.75
Feedback
Search any
task
Search any
task