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

141 models in chinese ranked by LMArena score · updated Nov 11, 2026

#ModelScore
1GLM-5.3Z.ai1535
2GLM-5.3-FlashZ.ai1528
3Kimi-K3Moonshot AI1527
4GLM-5.2Z.ai1522
5Kimi-K2.6Moonshot AI1521
6GLM-5.1Z.ai1516
7Kimi-K3.1-ProMoonshot AI1516
8GLM-5Z.ai1512
9MiMo-V2.5-ProXiaomi MiMo1507
10DeepSeek-V4.1-FlashDeepSeek1505
11GLM-4.6Z.ai1500
12NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1498
13Qwen3.5-397B-A17BQwen1498
14gemma-4-26B-A4B-itGoogle1495
15GLM-4.7Z.ai1494
16InklingThinking Machines1494
17Kimi-K2.5Moonshot AI1493
18Qwen3.8-27BQwen1493
19Hy3Tencent1490
20Qwen3-235B-A22B-Thinking-2507Qwen1482
21DeepSeek-V4-ProDeepSeek1481
22Qwen3.5-27BQwen1479
23gemma-4-31B-itGoogle1476
24MiMo-V2.5Xiaomi MiMo1470
25DeepSeek-V3.1DeepSeek1468
26GLM-4.5Z.ai1465
27MiniMax-M3MiniMax1465
28Qwen3-235B-A22B-Instruct-2507Qwen1465
29DeepSeek-V4-FlashDeepSeek1464
30MiMo-V2-FlashXiaomi MiMo1463
31Qwen3.5-122B-A10BQwen1463
32Inkling-SmallThinking Machines1462
33Qwen3-VL-235B-A22B-InstructQwen1462
34DeepSeek-V3.2-ExpDeepSeek1462
35Qwen3-Next-80B-A3B-InstructQwen1460
36Mistral-Large-4-1T-A52BMistral AI1457
37Qwen3.5-35B-A3BQwen1457
38DeepSeek-V3.2DeepSeek1455
39NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1451
40LongCat-Flash-ChatMeituan LongCat1449
41Step-3.5-FlashStepFun1446
42Mistral-Large-3-675B-Instruct-2512Mistral AI1446
43Mistral-Medium-3.5-128BMistral AI1444
44Qwen3-VL-235B-A22B-ThinkingQwen1442
45DeepSeek-R1-0528DeepSeek1442
46MiniMax-M2.7MiniMax1439
47Hy3-previewTencent1435
48Qwen3-30B-A3B-Instruct-2507Qwen1433
49NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA1432
50GLM-4.5-AirZ.ai1426
51Qwen3-235B-A22BQwen1424
52GLM-4.6VZ.ai1424
53granite-4.2-30bIBM Granite1423
54Ling-flash-2.0inclusionAI1419
55Muse-Glimmer-30Bmeta-models1410
56Qwen3-Next-80B-A3B-ThinkingQwen1406
57GLM-4.7-FlashZ.ai1403
58DeepSeek-R1DeepSeek1400
59Ring-flash-2.0inclusionAI1399
60MiniMax-M2.5MiniMax1393
61DeepSeek-V3-0324DeepSeek1390
62gpt-oss-120bOpenAI1385
63NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1385
64QwQ-32BQwen1378
65Trinity-Large-ThinkingArcee AI1373
66MiniMax-M2MiniMax1366
67NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA1365
68granite-4.2-8bIBM Granite1362
69Qwen3-32BQwen1357
70Qwen3-Coder-480B-A35B-InstructQwen1356
71INTELLECT-3Prime Intellect1355
72Trinity-Large-PreviewArcee AI1353
73Qwen3-30B-A3BQwen1347
74gemma-3-27b-itGoogle1346
75Mistral-Small-3.2-24B-Instruct-2506Mistral AI1340
76DeepSeek-V3DeepSeek1338
77GLM-4.5VZ.ai1337
78granite-4.1-8bIBM Granite1336
79DeepSeek-V2.5-1210DeepSeek1318
80gpt-oss-20bOpenAI1315
81gemma-3n-E4B-itGoogle1309
82Olmo-3.1-32B-InstructAi21304
83Olmo-3-32B-ThinkAi21299
84DeepSeek-V2.5DeepSeek1281
85granite-4.2-3bIBM Granite1279
86Llama-4-Maverick-17B-128E-InstructMeta Llama1278
87Qwen2.5-72B-InstructQwen1272
88Llama-3.1-Nemotron-70B-InstructNVIDIA1263
89Llama-4-Scout-17B-16E-InstructMeta Llama1255
90Mistral-Small-3.1-24B-Instruct-2503Mistral AI1253
91granite-4.0-h-smallIBM Granite1251
92Llama-3.1-Tulu-3-70BAi21249
93Llama-3.1-405B-InstructMeta Llama1242
94Olmo-3.1-32B-ThinkAi21241
95Qwen2-72B-InstructQwen1240
96Qwen2.5-Coder-32B-InstructQwen1222
97gemma-2-27b-itGoogle1221
98QwQ-32B-PreviewQwen1218
99Llama-3.3-70B-InstructMeta Llama1217
100Llama-3.1-70B-InstructMeta Llama1215
101Nemotron-4-340B-InstructNVIDIA1214
102phi-4Microsoft1212
103aya-expanse-32bCohere Labs1211
104Qwen1.5-110B-ChatQwen1206
105Mistral-Small-24B-Instruct-2501Mistral AI1204
106DeepSeek-Coder-V2-InstructDeepSeek1201
107Qwen1.5-72B-ChatQwen1186
108gemma-2-9b-itGoogle1185
109aya-expanse-8bCohere Labs1181
110Qwen1.5-32B-ChatQwen1177
111Llama-3.1-Tulu-3-8BAi21176
112Llama-3.1-8B-InstructMeta Llama1151
113Qwen1.5-14B-ChatQwen1147
114granite-3.1-8b-instructIBM Granite1145
115Qwen1.5-7B-ChatQwen1141
116granite-3.1-2b-instructIBM Granite1139
117gemma-2-2b-itGoogle1132
118deepseek-llm-67b-chatDeepSeek1132
119Mixtral-8x22B-Instruct-v0.1Mistral AI1116
120Meta-Llama-3-70B-InstructMeta Llama1114
121Phi-3-medium-4k-instructMicrosoft1108
122Qwen-14B-ChatQwen1077
123Meta-Llama-3-8B-InstructMeta Llama1076
124granite-3.0-2b-instructIBM Granite1070
125granite-3.0-8b-instructIBM Granite1063
126Phi-3-small-8k-instructMicrosoft1061
127gemma-1.1-7b-itGoogle1061
128Mixtral-8x7B-Instruct-v0.1Mistral AI1055
129gemma-7b-itGoogle1036
130Phi-3-mini-4k-instructMicrosoft1034
131Qwen1.5-4B-ChatQwen1024
132Llama-3.2-3B-InstructMeta Llama1017
133Phi-3-mini-128k-instructMicrosoft1016
134OLMo-7B-InstructAi21014
135gemma-1.1-2b-itGoogle1012
136Mistral-7B-Instruct-v0.2Mistral AI1009
137Llama-2-13b-chat-hfMeta Llama1001
138Llama-2-70b-chat-hfMeta Llama995
139gemma-2b-itGoogle986
140Llama-2-7b-chat-hfMeta Llama973
141Llama-3.2-1B-InstructMeta Llama959
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.