List your company

Multi-task Evaluation on Average (GSM8K-CoT, MATH, MBPP, HumanEval)

51.6AccuracyTAD-Q
43.845.82547.8549.875May 10, 2026

Evaluation results

MethodLinks
TAD-QBackbone=LLaDA, Configuration=Quality2026.0551.65.08225.2
TAD-SBackbone=LLaDA, Configuration=Speed2026.0549.95.76257.1
LLaDABackbone=LLaDA-Instruct2026.0546.2146.2
d3LLMBackbone=LLaDA2026.0545.96.25206.1
Fast-dLLMBackbone=LLaDA2026.0545.52.3684.7
dParallelBackbone=LLaDA2026.0545.53.9128.6
D2FBackbone=LLaDA2026.0544.12.4787.9