Neura Intelligence Index

AI Model Benchmarks

WinoGrande — AI Model Leaderboard & Results | Neura Market

Back to Leaderboard

WinoGrande

Large-scale Winograd schema challenge for commonsense reasoning

language0-100 percentSaturatedPaper / Website

Model Rankings (14)

#	Model	Score	Provider	Source
1	Llama 3.1 405B🇺🇸	87.6	Meta
2	GPT-4 Turbo🇺🇸	87.5	OpenAI
3	Nemotron 4 340B🇺🇸	86.2	NVIDIA
4	Llama 3.3 70B🇺🇸	86.1	Meta
5	GPT-4o🇺🇸	85.7	OpenAI
6	Claude 3 Opus🇺🇸	85.4	Anthropic
7	Llama 3.1 70B🇺🇸	85.3	Meta
8	Qwen 2.5 72B🇨🇳	84.8	Alibaba
9	Claude 3.5 Sonnet🇺🇸	83.2	Anthropic
10	GPT-4o mini🇺🇸	82.3	OpenAI
11	Mixtral 8x22B🇫🇷	82.1	Mistral
12	Phi-3 Medium🇺🇸	81.4	Microsoft
13	Command R+🇨🇦	80.2	Cohere
14	Llama 3.1 8B🇺🇸	78.9	Meta