List your company

Natural Language Inference on RTE (0-shot and 32-shot settings)

84.8Accuracy (0-shot)OPT-IML 175B
45.040855.362965.68576.0071Dec 22, 2022Jun 9, 2023Nov 25, 2023May 12, 2024Oct 28, 2024Apr 15, 2025Oct 2, 2025

Evaluation results

MethodLinks
OPT-IML 175BScale=175B2022.1284.883.8
OPT-IML 30BScale=30B2022.1283.873.3
OPT-IML 1.3BScale=1.3B2022.1266.848.7
DenseSparsity=0%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1065.34—
SparseGPTSparsity=50%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1064.26—
L-ADMMSparsity=50%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1063.18—
ALPSSparsity=50%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1062.82—
WandaSparsity=50%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1060.65—
SAFESparsity=50%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1060.65—
OPT 175BScale=175B2022.1260.371
ALPSSparsity=60%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1060.29—
L-ADMMSparsity=60%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1059.93—
WandaSparsity=60%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1059.57—
OPT 30BScale=30B2022.1258.161.7
SparseGPTSparsity=60%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1057.76—
SAFESparsity=60%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1057.4—
MagnitudeSparsity=50%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1055.96—
ELSASparsity=50%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1055.6—
OPT 1.3BScale=1.3B2022.1254.247.3
L-ADMMSparsity=90%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1053.79—
ELSASparsity=60%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1053.43—
L-ADMMSparsity=70%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1053.43—
ALPSSparsity=70%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1053.07—
MagnitudeSparsity=80%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1053.07—
MagnitudeSparsity=60%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
MagnitudeSparsity=70%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
WandaSparsity=70%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
SparseGPTSparsity=70%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
SAFESparsity=70%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
ELSASparsity=70%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
WandaSparsity=80%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
SparseGPTSparsity=80%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
L-ADMMSparsity=80%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
ALPSSparsity=80%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
SAFESparsity=80%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
ELSASparsity=80%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
WandaSparsity=90%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
ALPSSparsity=90%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
SAFESparsity=90%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
ELSASparsity=90%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.71—
SparseGPTSparsity=90%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1052.35—
MagnitudeSparsity=90%, Backbone=Llama-2 13B, Protocol=Zero-shot2025.1046.57—