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

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

#ModelScore
31Llama-4-Scout-17B-16E-InstructMeta Llama1249
30Llama-4-Maverick-17B-128E-InstructMeta Llama1266
29gemma-3-4b-itGoogle1270
28gemma-3n-E4B-itGoogle1287
27GLM-4.5VZ.ai1295
26gemma-3-12b-itGoogle1331
25Inkling-SmallThinking Machines1337
24Muse-Glimmer-30Bmeta-models1341
23Mistral-Large-4-1T-A52BMistral AI1343
22Qwen3-VL-235B-A22B-ThinkingQwen1344
21gemma-3-27b-itGoogle1345
20GLM-4.6VZ.ai1346
19Qwen3.5-35B-A3BQwen1347
18Inkling-2-SmallThinking Machines1348
17Qwen3.5-27BQwen1362
16Qwen3-VL-235B-A22B-InstructQwen1365
15Qwen3.5-122B-A10BQwen1368
14Qwen3.8-27BQwen1377
13NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1377
12MiMo-V2.5Xiaomi MiMo1391
Show all 31 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.