List your company
ResearchFormerly WizWand

Recognizing Textual Entailment on RTE (test)

76.53AccuracyQWEN3-14B
45.74653.73861.7369.722Apr 24, 2024Aug 9, 2024Nov 25, 2024Mar 13, 2025Jun 28, 2025Oct 14, 2025Jan 30, 2026
Updated 8mo ago

Evaluation results

MethodLinks
QWEN3-14BModel Architecture=QWEN3-14B, Configuration Type=Dense, Evaluation Protocol=Zero-shot, Sparsity Level=0%2026.0176.53—
QWEN3-4BModel Architecture=QWEN3-4B, Configuration Type=Dense, Evaluation Protocol=Zero-shot, Sparsity Level=0%2026.0176.53—
MISTRAL-7BModel Architecture=MISTRAL-7B, Configuration Type=Dense, Evaluation Protocol=Zero-shot, Sparsity Level=0%2026.0175.81—
DEEPSEEK-R1-QWEN-8BModel Architecture=DEEPSEEK-R1-QWEN-8B, Configuration Type=Dense, Evaluation Protocol=Zero-shot, Sparsity Level=0%2026.0174.37—
DEEPSEEK-R1-LLAMA-8BModel Architecture=DEEPSEEK-R1-LLAMA-8B, Configuration Type=Dense, Evaluation Protocol=Zero-shot, Sparsity Level=0%2026.0172.2—
LLAMA-3.1-8BModel Architecture=LLAMA-3.1-8B, Configuration Type=Dense, Evaluation Protocol=Zero-shot, Sparsity Level=0%2026.0171.12—
DenseBackbone=RoBERTa2024.0466.79—
NEPENTHEBackbone=RoBERTa2024.0466.06—
Smallest weightsBackbone=RoBERTa2024.0465.81—
DARTModel Architecture=DEEPSEEK-R1-QWEN-8B, Configuration Type=Sparse, Evaluation Protocol=Zero-shot, Sparsity Level=70%2026.0163.54—
DARTModel Architecture=MISTRAL-7B, Configuration Type=Sparse, Evaluation Protocol=Zero-shot, Sparsity Level=70%2026.0163.18—
IMPBackbone=RoBERTa2024.0462.82—
DARTModel Architecture=DEEPSEEK-R1-LLAMA-8B, Configuration Type=Sparse, Evaluation Protocol=Zero-shot, Sparsity Level=70%2026.0162.45—
Smallest gradientsBackbone=RoBERTa2024.0462.2—
DenseBackbone=BERT2024.0461.01—
NEPENTHEBackbone=BERT2024.0458.12—
IMPBackbone=BERT2024.0457.76—
EGPBackbone=BERT2024.0457.73—
DARTModel Architecture=LLAMA-3.1-8B, Configuration Type=Sparse, Evaluation Protocol=Zero-shot, Sparsity Level=70%2026.0155.23—
DARTModel Architecture=LLAMA-3.2-3B, Configuration Type=Sparse, Evaluation Protocol=Zero-shot, Sparsity Level=70%2026.0155.23—
Smallest gradientsBackbone=BERT2024.0455.23—
DARTModel Architecture=QWEN3-14B, Configuration Type=Sparse, Evaluation Protocol=Zero-shot, Sparsity Level=70%2026.0154.15—
LLAMA-3.2-3BModel Architecture=LLAMA-3.2-3B, Configuration Type=Dense, Evaluation Protocol=Zero-shot, Sparsity Level=0%2026.0154.15—
DARTModel Architecture=QWEN3-4B, Configuration Type=Sparse, Evaluation Protocol=Zero-shot, Sparsity Level=70%2026.0152.71—
EGPBackbone=RoBERTa2024.0452.71—
Smallest weightsBackbone=BERT2024.0446.93—