List your company

Multiple-choice QA on Multiple-Choice Suite

72.1MC AvgERNIE
-2.3868816.9510636.28955.62694Mar 6, 2026Mar 8, 2026Mar 10, 2026Mar 12, 2026Mar 14, 2026Mar 16, 2026Mar 19, 2026

Evaluation results

MethodLinks
ERNIESparsity=Full2026.0372.1
ESAPModel=ERNIE, Sparsity=25%, Criterion=EAN2026.0367.5
ESAPModel=ERNIE, Sparsity=25%, Criterion=REAP2026.0367.2
EANModel=ERNIE, Sparsity=25%, Allocation=UNI2026.0366.9
REAPModel=ERNIE, Sparsity=25%, Allocation=UNI2026.0366.7
OLMoESparsity=Full2026.0365.3
ESAPModel=ERNIE, Sparsity=25%, Criterion=Freq2026.0364.7
ESAPModel=ERNIE, Sparsity=25%, Criterion=SEER2026.0363.8
FreqModel=ERNIE, Sparsity=25%, Allocation=UNI2026.0363.6
SEERModel=ERNIE, Sparsity=25%, Allocation=UNI2026.0363.4
EANModel=ERNIE, Sparsity=50%, Allocation=UNI2026.0358.5
ESAPModel=ERNIE, Sparsity=50%, Criterion=EAN2026.0358.2
ESAPModel=OLMoE, Sparsity=25%, Criterion=REAP2026.0358.1
REAPModel=OLMoE, Sparsity=25%, Allocation=UNI2026.0357.9
REAPModel=ERNIE, Sparsity=50%, Allocation=UNI2026.0357.5
ESAPModel=ERNIE, Sparsity=50%, Criterion=REAP2026.0357.5
FreqModel=ERNIE, Sparsity=50%, Allocation=UNI2026.0356.5
ESAPModel=ERNIE, Sparsity=50%, Criterion=Freq2026.0355.7
EANModel=OLMoE, Sparsity=25%, Allocation=UNI2026.0355.1
SEERModel=ERNIE, Sparsity=50%, Allocation=UNI2026.0355.1
FreqModel=OLMoE, Sparsity=25%, Allocation=UNI2026.0354.7
ESAPModel=ERNIE, Sparsity=50%, Criterion=SEER2026.0354.7
SEERModel=OLMoE, Sparsity=25%, Allocation=UNI2026.0354.5
ESAPModel=OLMoE, Sparsity=25%, Criterion=EAN2026.0354.3
ESAPModel=OLMoE, Sparsity=25%, Criterion=SEER2026.0353.9
ESAPModel=OLMoE, Sparsity=25%, Criterion=Freq2026.0353.9
FullModel=ERNIE-21B, Pruning Ratio=0%, Protocol=Zero-shot2026.030.721
EANModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.687
REAPModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.685
AIMERModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.681
RandomModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.664
SEERModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.658
FrequencyModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.655
FullModel=OLMoE-7B, Pruning Ratio=0%, Protocol=Zero-shot2026.030.653
MagnitudeModel=ERNIE-21B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.648
EANModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.030.605
AIMERModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.6
AIMERModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.030.598
REAPModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.030.592
REAPModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.588
RandomModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.030.584
EANModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.577
SEERModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.564
RandomModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.562
FrequencyModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.56
FrequencyModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.030.557
SEERModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.030.543
MagnitudeModel=ERNIE-21B, Pruning Ratio=50%, Protocol=Zero-shot2026.030.503
MagnitudeModel=OLMoE-7B, Pruning Ratio=25%, Protocol=Zero-shot2026.030.478