Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Fine-grained visual understanding on MME RealWorld
Loading...
65.3
Score
SwimBird
56.46
58.755
61.05
63.345
Feb 5, 2026
Score
Updated 3d ago
Evaluation Results
Method
Method
Links
Score
SwimBird
Backbone=Qwen3-VL 8B
2026.02
65.3
DeepEyesV2
Model Category=Multimo...
2026.02
64.9
Thyme
Model Category=Multimo...
2026.02
64.8
Pixel Reasoner
Model Category=Multimo...
2026.02
64.4
DeepEyes
Model Category=Multimo...
2026.02
64.1
GPT-4o
Model Category=Textual...
2026.02
62.8
Qwen3-VL-8B-Instruct
Model Category=Textual...
2026.02
61.9
Qwen2.5-VL-32B-Instruct
Model Category=Textual...
2026.02
59.1
LLaVA-OneVison
Model Category=Textual...
2026.02
57.4
Qwen2.5-VL-7B-Instruct
Model Category=Textual...
2026.02
56.8
Feedback
Search any
task
Search any
task