Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering on OBQA (Acc, Gap)
Loading...
90.1
Accuracy
SALAD-7B
54.22
63.535
72.85
82.165
Aug 14, 2025
Aug 24, 2025
Sep 3, 2025
Sep 14, 2025
Sep 24, 2025
Oct 4, 2025
Oct 15, 2025
Accuracy
Gap
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
Gap
SALAD-7B
Input Modality=Text, P...
2025.10
90.1
-1.1
Qwen2.5-Omni-7B
Input Modality=Text, P...
2025.10
87.3
1.7
SALAD-3B
Input Modality=Text, P...
2025.10
83.7
-1.9
DiVA-Llama3.1-8B
Input Modality=Text, P...
2025.10
82
1.3
Qwen2-Audio-7B
Input Modality=Text, P...
2025.10
73.4
3.3
GLM-4-Voice-9B
Input Modality=Text, P...
2025.10
69.9
17.8
MSRS
Backbone=Mistral-7B-v0.3
2025.08
62.2
-
MSRS
Backbone=Qwen2-7B-Inst...
2025.08
61.6
-
Vanilla
Backbone=Qwen2-7B-Inst...
2025.08
60.6
-
Vanilla
Backbone=Mistral-7B-v0.3
2025.08
60.2
-
MSRS
Backbone=Llama-3-8B-In...
2025.08
56.8
-
Vanilla
Backbone=Llama-3-8B-In...
2025.08
55.6
-
Feedback
Search any
task
Search any
task