List your company

General Reasoning on HellaSwag (test)

85.34HellaSwag ScoreLLaDA-8B
23.626439.648255.6771.6918Dec 28, 2025Jan 10, 2026Jan 24, 2026Feb 6, 2026Feb 20, 2026Mar 5, 2026Mar 19, 2026

Evaluation results

MethodLinks
LLaDA-8BModel Type=DLLM Baseline, Few-shot setting=10-shot2025.1285.34
Qwen3-8BModel Type=AR Baseline, Few-shot setting=10-shot2025.1285.27
Qwen2.5-7B-Inst.Parameters=7B2026.0385.2
VEPO-7B (Full)Parameters=7B, Configuration=Full2026.0385.2
WeDLM-7BModel Type=WeDLM (Ours), Base Model=Qwen2.5-7B, Few-shot setting=10-shot2025.1285.11
WeDLM-8BModel Type=WeDLM (Ours), Base Model=Qwen3-8B, Few-shot setting=10-shot2025.1284.55
VEPO-7B-SFTParameters=7B, Stage=SFT2026.0383.7
VEPO-7B w/o CPTParameters=7B, CPT=excluded2026.0383.5
Qwen2.5-7BModel Type=AR Baseline, Few-shot setting=10-shot2025.1280.2
Dream-7BModel Type=DLLM Baseline, Few-shot setting=10-shot2025.1278.05
Tower-Plus-9BParameters=9B2026.0373.1
Apertus-8B-Inst.Parameters=8B2026.0364.2
Gemma3-27B-ITParameters=27B2026.0355.9
Qwen3-8BParameters=8B2026.0326