Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning and Generation on DriveLM (test)
Loading...
81
Accuracy
Vanilla
77.88
78.69
79.5
80.31
Apr 21, 2026
Accuracy
ChatGPT Score
BLEU-4
ROUGE
CIDEr
Match Rate
Average Score
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
ChatGPT Score
BLEU-4
ROUGE
CIDEr
Match Rate
Average Score
Vanilla
Token Retention Rate=F...
2026.04
81
65.44
61
74
29
33.9
59.1
ST-Prune
Token Retention Rate=R...
2026.04
81
64.48
62
75
20
34.9
58.8
Prune2Drive
Token Retention Rate=R...
2026.04
80
64.92
60
75
20
34
58.3
Prune2Drive
Token Retention Rate=R...
2026.04
78
64.52
56
74
16
33.4
57.4
ST-Prune
Token Retention Rate=R...
2026.04
78
64.72
61
74
23
33.6
57.9
Feedback
Search any
task
Search any
task