List your company
ResearchFormerly WizWand

Natural Language Inference on SNLI-Neg

75.9AccuracyOpenAI o1
44.80452.87760.9569.023Apr 21, 2026
Updated 6mo ago

Evaluation results

MethodLinks
OpenAI o1# Params.=—, Evaluation Setting=In-context learning, Prompting Strategy=Zero-shot2026.0475.9
GPT-4o# Params.=—, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot2026.0474.8
Qwen2 7B# Params.=7B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot, Pre-training Corpus=Best of (¬ATOMIC, ¬ANION)2026.0472.4
Llama 3.1 70B# Params.=70B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot2026.0469.1
Llama 3.1 8B# Params.=8B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot, Pre-training Corpus=Best of (¬ATOMIC, ¬ANION)2026.0468.2
Qwen2 7B# Params.=7B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot, Pre-training Corpus=ATOMIC + ANION2026.0466.5
Qwen2 7B# Params.=7B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot2026.0460.7
RoBERTa-large# Params.=355M, Evaluation Setting=Fully supervised, Pre-training Corpus=Best of (¬ATOMIC, ¬ANION)2026.0458.3
Llama 3.1 8B# Params.=8B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot, Pre-training Corpus=ATOMIC + ANION2026.0457.5
RoBERTa-large-NSP# Params.=355M, Evaluation Setting=Fully supervised2026.0456.5
RoBERTa-large# Params.=355M, Evaluation Setting=Fully supervised, Pre-training Corpus=ATOMIC + ANION2026.0456.5
RoBERTa-large# Params.=355M, Evaluation Setting=Fully supervised2026.0456
Llama 3.1 8B# Params.=8B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot2026.0454.4
BERTNOT# Params.=110M, Evaluation Setting=Fully supervised2026.0446