Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
General Perception on GQA
Loading...
71
Accuracy
THINKLITE-VL
49.888
55.369
60.85
66.331
May 22, 2026
Accuracy
Updated 9d ago
Evaluation Results
Method
Method
Links
Accuracy
THINKLITE-VL
Method=THINKLITE-VL
2026.05
71
LLAVA-NEXT-LLAMA3-8B
Backbone=LLAVA-NEXT-LL...
2026.05
69.3
INTERNVL3-8B + PGT
Backbone=INTERNVL3-8B,...
2026.05
68.3
LLAVA-NEXT-LLAMA3-8B + PGT
Backbone=LLAVA-NEXT-LL...
2026.05
68.1
QWEN2.5-VL-7B + PGT
Backbone=QWEN2.5-VL-7B...
2026.05
67.1
INTERNVL3-8B
Backbone=INTERNVL3-8B
2026.05
66.8
LLAVA-NEXT-7B
Backbone=LLAVA-NEXT-7B
2026.05
66.7
LLAVA-NEXT-7B + PGT
Backbone=LLAVA-NEXT-7B...
2026.05
66.5
QWEN2.5-VL-7B + SPECIALIZED MIX
Backbone=QWEN2.5-VL-7B...
2026.05
66.2
IMAGE JIGSAW
Method=IMAGE JIGSAW
2026.05
66.2
QWEN2.5-VL-7B
Backbone=QWEN2.5-VL-7B
2026.05
65.8
QWEN2.5-VL-3B + PGT
Backbone=QWEN2.5-VL-3B...
2026.05
65.4
QWEN2.5-VL-3B + SPECIALIZED MIX
Backbone=QWEN2.5-VL-3B...
2026.05
65.2
QWEN2.5-VL-3B
Backbone=QWEN2.5-VL-3B
2026.05
64.9
SPATIAL-LADDER-3B
Method=SPATIAL-LADDER-3B
2026.05
52
VIGORL-3B
Method=VIGORL-3B
2026.05
50.7
Feedback
Search any
task
Search any
task