Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Vision-Language Reasoning on nuScenes (reasoning)
Loading...
67
BERT F1 Score
Qwen1.5-0.5B
53.48
56.99
60.5
64.01
Mar 15, 2026
BERT F1 Score
BERT Precision
BERT Recall
ROUGE-1
ROUGE-2
ROUGE-L
BLEU-1
BLEU-2
BLEU-3
Updated 1mo ago
Evaluation Results
Method
Method
Links
BERT F1 Score
BERT Precision
BERT Recall
ROUGE-1
ROUGE-2
ROUGE-L
BLEU-1
BLEU-2
BLEU-3
Qwen1.5-0.5B
2026.03
67
68
66
47
19
34
36
22
15
Qwen1.5-0.5B
behavior generation to...
2026.03
67
68
66
47
19
34
36
22
15
Qwen2-1.5B
2026.03
67
68
66
29
11
20
17
10
6
Qwen1.5-0.5B
zero-shot evaluation=true
2026.03
54
64
52
9
3
7
4
2
3
Feedback
Search any
task
Search any
task