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
1Kimi-K3Moonshot AI1453
2GLM-5.3-FlashZ.ai1442
3Kimi-K3.1-ProMoonshot AI1439
4DeepSeek-V4.1-FlashDeepSeek1438
5Kimi-K2.6Moonshot AI1433
6Kimi-K2.5Moonshot AI1422
7gemma-4-31B-itGoogle1415
8Qwen3.5-397B-A17BQwen1402
9gemma-4-26B-A4B-itGoogle1402
10InklingThinking Machines1395
11MiniMax-M3MiniMax1395
12MiMo-V2.5Xiaomi MiMo1391
13NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1377
14Qwen3.8-27BQwen1377
15Qwen3.5-122B-A10BQwen1368
16Qwen3-VL-235B-A22B-InstructQwen1365
17Qwen3.5-27BQwen1362
18Inkling-2-SmallThinking Machines1348
19Qwen3.5-35B-A3BQwen1347
20GLM-4.6VZ.ai1346
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.