Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Chain-of-Thought Reasoning on Driving Evaluation Benchmark
Loading...
0.88
GPT Score
UniUGP
0.5368
0.6259
0.715
0.8041
Dec 10, 2025
GPT Score
BLEU Score
Updated 4d ago
Evaluation Results
Method
Method
Links
GPT Score
BLEU Score
UniUGP
full model=true
2025.12
0.88
0.24
UniUGP (w/o CoT)
Chain-of-Thought modul...
2025.12
0.83
0.218
UniUGP (w/o Gen.)
generation module=excl...
2025.12
0.8
0.203
Qwen-2.5-VL-72B
historical trajectory...
2025.12
0.72
0.188
GPT-4o
historical trajectory...
2025.12
0.55
0.125
Feedback
Search any
task
Search any
task