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

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

#ModelScore
68gpt-oss-20bOpenAI1202
67granite-4.2-3bIBM Granite1204
66Olmo-3.1-32B-ThinkAi21227
65granite-4.2-8bIBM Granite1235
64Olmo-3-32B-ThinkAi21254
63NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA1259
62NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1270
61Qwen3-30B-A3BQwen1271
60gpt-oss-120bOpenAI1274
59granite-4.2-30bIBM Granite1285
58MiniMax-M2MiniMax1287
57QwQ-32BQwen1287
56Ling-flash-2.0inclusionAI1287
55GLM-4.5VZ.ai1295
54GLM-4.7-FlashZ.ai1296
53Qwen3-32BQwen1297
52Trinity-Large-ThinkingArcee AI1308
51Qwen3-Next-80B-A3B-ThinkingQwen1315
50NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA1315
49INTELLECT-3Prime Intellect1317
Show all 68 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.