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
1GLM-5.2Z.ai1459
2GLM-5.3Z.ai1459
3GLM-5.1Z.ai1453
4GLM-5.3-FlashZ.ai1442
5DeepSeek-V4.1-FlashDeepSeek1438
6MiMo-V2.5-ProXiaomi MiMo1437
7GLM-5Z.ai1437
8Kimi-K2.6Moonshot AI1433
9Kimi-K2.5Moonshot AI1422
10gemma-4-31B-itGoogle1415
11GLM-4.6Z.ai1412
12DeepSeek-R1-0528DeepSeek1405
13Hy3Tencent1405
14DeepSeek-V3.1-TerminusDeepSeek1403
15DeepSeek-V3.2-ExpDeepSeek1403
16GLM-4.7Z.ai1402
17Qwen3.5-397B-A17BQwen1402
18gemma-4-26B-A4B-itGoogle1402
19DeepSeek-V3.1DeepSeek1401
20NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1399
21InklingThinking Machines1395
22MiniMax-M3MiniMax1395
23GLM-4.5Z.ai1395
24MiMo-V2.5Xiaomi MiMo1391
25Beam-1.0-501B-A23Breflection1388
26Mistral-Large-3-675B-Instruct-2512Mistral AI1386
27Qwen3-235B-A22B-Thinking-2507Qwen1384
28NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1377
29Qwen3.8-27BQwen1377
30MiMo-V2-FlashXiaomi MiMo1376
31Mistral-Medium-3.5-128BMistral AI1374
32Qwen3.5-122B-A10BQwen1368
33Qwen3.5-27BQwen1362
34Qwen3-235B-A22BQwen1357
35Step-3.5-FlashStepFun1357
36DeepSeek-R1DeepSeek1354
37MiniMax-M2.7MiniMax1354
38Inkling-2-SmallThinking Machines1348
39Qwen3.5-35B-A3BQwen1347
40GLM-4.6VZ.ai1346
41LongCat-Flash-ChatMeituan LongCat1345
42Qwen3-VL-235B-A22B-ThinkingQwen1344
43GLM-4.5-AirZ.ai1343
44Mistral-Large-4-1T-A52BMistral AI1343
45Muse-Glimmer-30Bmeta-models1341
46Hy3-previewTencent1340
47Inkling-SmallThinking Machines1337
48MiniMax-M2.5MiniMax1330
49INTELLECT-3Prime Intellect1317
50NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA1315
51Qwen3-Next-80B-A3B-ThinkingQwen1315
52Trinity-Large-ThinkingArcee AI1308
53Qwen3-32BQwen1297
54GLM-4.7-FlashZ.ai1296
55GLM-4.5VZ.ai1295
56Ling-flash-2.0inclusionAI1287
57QwQ-32BQwen1287
58MiniMax-M2MiniMax1287
59granite-4.2-30bIBM Granite1285
60gpt-oss-120bOpenAI1274
61Qwen3-30B-A3BQwen1271
62NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1270
63NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA1259
64Olmo-3-32B-ThinkAi21254
65granite-4.2-8bIBM Granite1235
66Olmo-3.1-32B-ThinkAi21227
67granite-4.2-3bIBM Granite1204
68gpt-oss-20bOpenAI1202
Show the top 20

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.