List your company
ResearchFormerly WizWand

Natural Language Inference on MNLI Neg

75AccuracyGPT-4o
45.8853.446168.56Apr 21, 2026
Updated 6mo ago

Evaluation results

MethodLinks
GPT-4o# Params.=—, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot2026.0475
OpenAI o1# Params.=—, Evaluation Setting=In-context learning, Prompting Strategy=Zero-shot2026.0474.6
RoBERTa-large-NSP# Params.=355M, Evaluation Setting=Fully supervised2026.0469.9
RoBERTa-large# Params.=355M, Evaluation Setting=Fully supervised2026.0469.9
RoBERTa-large# Params.=355M, Evaluation Setting=Fully supervised, Pre-training Corpus=Best of (¬ATOMIC, ¬ANION)2026.0469.7
RoBERTa-large# Params.=355M, Evaluation Setting=Fully supervised, Pre-training Corpus=ATOMIC + ANION2026.0469.4
Qwen2 7B# Params.=7B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot, Pre-training Corpus=Best of (¬ATOMIC, ¬ANION)2026.0467.5
Llama 3.1 70B# Params.=70B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot2026.0465.9
Llama 3.1 8B# Params.=8B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot, Pre-training Corpus=Best of (¬ATOMIC, ¬ANION)2026.0463.9
Qwen2 7B# Params.=7B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot, Pre-training Corpus=ATOMIC + ANION2026.0463
BERTNOT# Params.=110M, Evaluation Setting=Fully supervised2026.0460.9
Qwen2 7B# Params.=7B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot2026.0459.5
Llama 3.1 8B# Params.=8B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot, Pre-training Corpus=ATOMIC + ANION2026.0451.1
Llama 3.1 8B# Params.=8B, Evaluation Setting=In-context learning, Prompting Strategy=Few-shot2026.0447