Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Scene Captioning on SC Dataset zero-shot
Loading...
66.19
BLEU-1
LiDAR-LLM
28.0532
37.9541
47.855
57.7559
Feb 28, 2026
BLEU-1
BERT-P
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU-1
BERT-P
LiDAR-LLM
Modality=L, Params=6.96B
2026.02
66.19
88.47
Wild-Drive-3B
Modality=V-L, Params=3...
2026.02
65.45
93.64
Wild-Drive-0.5B
Modality=V-L, Params=0...
2026.02
63.25
89.53
BEV-LLM-8B
Modality=V-L, Params=8...
2026.02
61.26
88.91
BEV-LLM-1B
Modality=V-L, Params=1...
2026.02
59.07
87.32
LLama-AdapterV2
Modality=V, Params=7.22B
2026.02
46.33
79.92
Instruct-BLIP
Modality=V, Params=7.91B
2026.02
33.41
70.52
LLaVA1.5
Modality=V, Params=7.06B
2026.02
33.27
71.55
Mini-GPT4
Modality=V, Params=7B
2026.02
29.52
74.26
Feedback
Search any
task
Search any
task