List your company

STEM Reasoning on GPQA-Diamond 5-shot

57.3AccuracyERNIE 5.0-Base
23.96832.621541.27549.9285Dec 28, 2025Jan 3, 2026Jan 9, 2026Jan 16, 2026Jan 22, 2026Jan 28, 2026Feb 4, 2026

Evaluation results

MethodLinks
ERNIE 5.0-BaseNumber of shots=5-shot2026.0257.3
DS V3.2-Exp-BaseNumber of shots=5-shot2026.0253.01
Kimi K2-BaseNumber of shots=5-shot2026.0248.1
WeDLM-8BInstruct Model=true, Model Category=WeDLM, Shot Configuration=5-shot, Inference Framework=vLLM, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.1244.95
Qwen3-8BInstruct Model=true, Model Category=AR Baseline, Shot Configuration=5-shot, Inference Framework=vLLM, Sampling Temperature=0.1, Max Generation Length=5122025.1241.41
SDAR-8BInstruct Model=true, Model Category=DLLM Baseline, Shot Configuration=5-shot, Inference Framework=JetEngine, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.1238.38
Dream-7BInstruct Model=true, Model Category=DLLM Baseline, Shot Configuration=5-shot, Inference Framework=dInfer, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.1235.86
WeDLM-7BInstruct Model=true, Model Category=WeDLM, Shot Configuration=5-shot, Inference Framework=vLLM, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.1233.84
Qwen2.5-7BInstruct Model=true, Model Category=AR Baseline, Shot Configuration=5-shot, Inference Framework=vLLM, Sampling Temperature=0.1, Max Generation Length=5122025.1227.1
LLaDA-8BInstruct Model=true, Model Category=DLLM Baseline, Shot Configuration=5-shot, Inference Framework=dInfer, Sampling Temperature=0.1, Max Generation Length=512, Window Size (W)=6, Penalty Coefficient (λ)=0.12025.1225.25