Through an API

Open and closed models answer the same suite-standard 1.0 through their APIs, ranked together. 1 ranked model.

#ModelPass rate
1DeepSeek V4.1 Flash 1017Open weights100%

Model leaderboard

148 models in non-english ranked by LMArena score · updated Nov 11, 2026

#ModelScore
148gemma-2b-itGoogle958
147Llama-2-7b-chat-hfMeta Llama973
146Llama-3.2-1B-InstructMeta Llama973
145OLMo-7B-InstructAi2977
144Qwen1.5-4B-ChatQwen979
143gemma-1.1-2b-itGoogle988
142gemma-7b-itGoogle999
141Phi-3-mini-128k-instructMicrosoft1000
140Mistral-7B-Instruct-v0.2Mistral AI1012
139SOLAR-10.7B-Instruct-v1.0Upstage1014
138Llama-3.2-3B-InstructMeta Llama1019
137Phi-3-mini-4k-instructMicrosoft1021
136Llama-2-13b-chat-hfMeta Llama1024
135granite-3.0-2b-instructIBM Granite1033
134granite-3.0-8b-instructIBM Granite1037
133Qwen-14B-ChatQwen1041
132Llama-2-70b-chat-hfMeta Llama1045
131gemma-1.1-7b-itGoogle1052
130Phi-3-small-8k-instructMicrosoft1058
129Qwen1.5-7B-ChatQwen1058
Show all 148 models

Score by size

Plot against
Best for its size

Scores: LMArena, CC BY 4.0. Measured on served versions, not local builds. A model with several served variants shows its best.