Share your thoughts, 1 month free Claude Pro on usSee more

Natural Language Inference on MNLI Neg

75Accuracy

GPT-4o

Updated 3mo ago

Evaluation Results

Method	Links
GPT-4o 2026.04		75
OpenAI o1 2026.04		74.6
RoBERTa-large-NSP 2026.04		69.9
RoBERTa-large 2026.04		69.9
RoBERTa-large 2026.04		69.7
RoBERTa-large 2026.04		69.4
Qwen2 7B 2026.04		67.5
Llama 3.1 70B 2026.04		65.9
Llama 3.1 8B 2026.04		63.9
Qwen2 7B 2026.04		63
BERTNOT 2026.04		60.9
Qwen2 7B 2026.04		59.5
Llama 3.1 8B 2026.04		51.1
Llama 3.1 8B 2026.04		47