Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Prevention Reasoning on AITP 1.0 (test)

0.0441BLEU

AITP

0.026940.0313950.035850.040305Apr 11, 2026
Updated 1mo ago

Evaluation Results

MethodLinks
2026.04
0.04410.19110.64510.56730.657
2026.04
0.03940.16760.63460.6340.5747
2026.04
0.03550.1830.6180.52760.4609
2026.04
0.0310.13060.63370.61130.756
2026.04
0.02760.14090.63670.60740.7338