Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Visual QA on EndoVis18 VQA standard (test)
Loading...
54.8
BLEU-4
Object Tokens (Ours)
36.7248
41.4174
46.11
50.8026
Jun 14, 2026
BLEU-4
CIDEr
ROUGE-L
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU-4
CIDEr
ROUGE-L
Object Tokens (Ours)
2026.06
54.8
6.049
81.57
EndoChat
In-domain model=true
2026.06
52.2
5.99
79.62
Gemma-3-12B
Fine-tuned=true
2026.06
52.15
5.919
78.36
LLaMA-3.2-11B
Fine-tuned=true
2026.06
49.87
4.549
78.36
GLM-4V-9B
Fine-tuned=true
2026.06
37.42
3.16
54.47
Feedback
Search any
task
Search any
task