Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Region-Based QA on EndoVis18 VQA standard (test)
Loading...
60.73
BLEU-4
Object Tokens (Ours)
34.5636
41.3568
48.15
54.9432
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
60.73
6.534
83.26
Gemma-3-12B
Fine-tuned=true
2026.06
60.64
5.48
80.64
EndoChat
In-domain model=true
2026.06
59.65
5.574
81.21
LLaMA-3.2-11B
Fine-tuned=true
2026.06
59.56
5.374
80.42
GLM-4V-9B
Fine-tuned=true
2026.06
35.57
3.259
57.62
Feedback
Search any
task
Search any
task