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

338 models in creative writing ranked by LMArena score · updated Nov 11, 2026

#ModelScore
338Qwen1.5-4B-ChatQwen969
337gemma-2b-itGoogle986
336OLMo-7B-InstructAi2990
335PaLM 2Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.991
334gemma-1.1-2b-itGoogle998
333gemma-7b-itGoogle1023
332Phi-3-mini-128k-instructMicrosoft1024
331Qwen-14B-ChatQwen1028
330Llama-3.2-1B-InstructMeta Llama1033
329Llama-2-7b-chat-hfMeta Llama1033
328Qwen1.5-7B-ChatQwen1034
327GPT-3.5 Turbo (1106)Closed. Closed weights: ranked by its LMArena score, with no size or downloads to show.1035
326Phi-3-mini-4k-instructMicrosoft1044
325granite-3.0-2b-instructIBM Granite1046
324Llama-2-13b-chat-hfMeta Llama1047
323gemma-1.1-7b-itGoogle1059
322deepseek-llm-67b-chatDeepSeek1067
321Mistral-7B-Instruct-v0.2Mistral AI1068
320granite-3.0-8b-instructIBM Granite1071
319Llama-2-70b-chat-hfMeta Llama1075
Show all 338 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.