List your company

Mathematical Reasoning on MATH500 (Acc (%), TPF, AUP)

63.6AccuracySDAR-8B-b32
27.30436.72746.1555.573Mar 4, 2026

Evaluation results

MethodLinks
SDAR-8B-b32Model Category=Block-wise dLLMs, Evaluation Protocol=4-shot2026.0363.64.81299.5
LightningRL-8B-b32Model Category=Block-wise dLLMs, Evaluation Protocol=4-shot2026.03636.28407.5
Fast-dLLM-v2Model Category=Block-wise dLLMs, Evaluation Protocol=4-shot2026.0348.72.61126.7
Qwen-2.5-7B-itModel Category=AR Models, Evaluation Protocol=4-shot2026.0341.4141.1
EAGLE-3 (LLaMA-3.1)Model Category=AR Models, Evaluation Protocol=4-shot2026.0339.85.72142.1
DreamModel Category=dLLMs, Evaluation Protocol=4-shot2026.0339.6139.6
dParallel-DreamModel Category=dLLMs, Evaluation Protocol=4-shot2026.0338.72.9477.9
Fast-dLLM-DreamModel Category=dLLMs, Evaluation Protocol=4-shot2026.0338.31.7855.2
d3LLM-DreamModel Category=dLLMs, Evaluation Protocol=4-shot2026.0338.23.9297.5
LLaDAModel Category=dLLMs, Evaluation Protocol=4-shot2026.0332.2132.2
Fast-dLLM-LLaDAModel Category=dLLMs, Evaluation Protocol=4-shot2026.0330.81.9747.2
d3LLM-LLaDAModel Category=dLLMs, Evaluation Protocol=4-shot2026.0330.45.74107.6
dParallel-LLaDAModel Category=dLLMs, Evaluation Protocol=4-shot2026.0330.23.1764.5
D2F-LLaDAModel Category=dLLMs, Evaluation Protocol=4-shot2026.0328.72.3845.5