Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning on MME-r reasoning
Loading...
722.5
Score
Qwen3-VL-8B-Thinking
-1.236
186.657
374.55
562.443
Feb 18, 2026
Mar 7, 2026
Mar 24, 2026
Apr 10, 2026
Apr 27, 2026
May 14, 2026
Jun 1, 2026
Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Score
Qwen3-VL-8B-Thinking
Backbone=Qwen3-VL-8B,...
2026.02
722.5
SAP
Backbone=Qwen3-VL-8B,...
2026.02
689.9
Qwen3-VL-8B-Instruct
Backbone=Qwen3-VL-8B,...
2026.02
656.7
MiMo-VL-7B-SFT
Run=+TRON
2026.06
46.46
Qwen3-VL-4B-Instruct
Run=+TRON
2026.06
45.88
MiMo-VL-7B-SFT
Run=Base
2026.06
45.29
Qwen3-VL-4B-Instruct
Run=Base
2026.06
42.85
Qwen2.5-VL-7B-Instruct
Run=+TRON
2026.06
28.62
Qwen2.5-VL-7B-Instruct
Run=Base
2026.06
26.6
Feedback
Search any
task
Search any
task