Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Prevention Reasoning on AITP 1.0 (test)
Loading...
0.0441
BLEU
AITP
0.02694
0.031395
0.03585
0.040305
Apr 11, 2026
BLEU
ROUGE-L
BERTScore
MoverScore
GPTEval
Updated 1mo ago
Evaluation Results
Method
Method
Links
BLEU
ROUGE-L
BERTScore
MoverScore
GPTEval
AITP
Model Type=Traffic-spe...
2026.04
0.0441
0.1911
0.6451
0.5673
0.657
Qwen3-VL
Model Type=General MLL...
2026.04
0.0394
0.1676
0.6346
0.634
0.5747
InternVL 3.5
Model Type=General MLL...
2026.04
0.0355
0.183
0.618
0.5276
0.4609
Gemma-3n-E4B
Model Type=General MLL...
2026.04
0.031
0.1306
0.6337
0.6113
0.756
Kimi-VL-A3B
Model Type=General MLL...
2026.04
0.0276
0.1409
0.6367
0.6074
0.7338
Feedback
Search any
task
Search any
task