Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multimodal Reasoning on Unifybench++
Loading...
74.6
BLEU
GPT-4o+TP
18.44
33.02
47.6
62.18
May 11, 2026
BLEU
GPT Score/Metric
Updated 2mo ago
Evaluation Results
Method
Method
Links
BLEU
GPT Score/Metric
GPT-4o+TP
Model Size=200B, Metho...
2026.05
74.6
-
GPT-4o+IP
Model Size=200B, Metho...
2026.05
74.5
-
RAP-MLLM
Model Size=13B, Method...
2026.05
33.2
-
Yo’LLaVA
Model Size=13B, Method...
2026.05
32.7
-
MC-LLaVA
Model Size=13B, Method...
2026.05
29.7
-
Sync-R1
Model Size=1.3B, Metho...
2026.05
25
-
UniCTokens
Model Size=1.3B, Metho...
2026.05
23.8
-
Yo’Chameleon
Model Size=7B, Method...
2026.05
23.1
-
Yo’LLaVA(Phi-1.5)
Model Size=1.3B, Metho...
2026.05
22.5
-
Qwen2.5-VL + TP
Model Size=3B, Method...
2026.05
21.8
-
Show-o+TP
Model Size=1.3B, Metho...
2026.05
21.7
-
Chameleon+IP
Model Size=7B, Method...
2026.05
21.6
-
Chamaleon+TP
Model Size=7B, Method...
2026.05
20.6
-
Feedback
Search any
task
Search any
task