List your company

General Question Answering on ExpertQA

0.2385RewardDAPO+START
0.1827560.1972280.21170.226172Mar 21, 2026

Evaluation results

MethodLinks
DAPO+STARTConfiguration=DAPO+START2026.030.238565.29
DAPOConfiguration=DAPO2026.030.2352—
GRPO+STARTEvaluation Protocol=Post-trained2026.030.220159.24
GRPOEvaluation Protocol=Post-trained2026.030.2182—
GRPO-MAEvaluation Protocol=Post-trained2026.030.21434.08
GRPO+STARTEvaluation Protocol=T_post + A_pre2026.030.187668.15
GRPO-MAEvaluation Protocol=T_post + A_pre2026.030.185954.14
GRPOEvaluation Protocol=T_post + A_pre2026.030.1849—