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

Natural Language Inference on SNLI-Neg

75.9Accuracy

OpenAI o1

Updated 3mo ago

Evaluation Results

Method	Links
OpenAI o1 2026.04		75.9
GPT-4o 2026.04		74.8
Qwen2 7B 2026.04		72.4
Llama 3.1 70B 2026.04		69.1
Llama 3.1 8B 2026.04		68.2
Qwen2 7B 2026.04		66.5
Qwen2 7B 2026.04		60.7
RoBERTa-large 2026.04		58.3
Llama 3.1 8B 2026.04		57.5
RoBERTa-large-NSP 2026.04		56.5
RoBERTa-large 2026.04		56.5
RoBERTa-large 2026.04		56
Llama 3.1 8B 2026.04		54.4
BERTNOT 2026.04		46