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

86 models in coding ranked by LMArena score · updated Nov 11, 2026

#ModelScore
1GLM-5.3-FlashZ.ai1509
2DeepSeek-V4.1-FlashDeepSeek1504
3MiMo-V2.5-ProXiaomi MiMo1501
4GLM-5.3Z.ai1499
5Kimi-K2.6Moonshot AI1489
6GLM-5.2Z.ai1488
7GLM-5.1Z.ai1485
8Kimi-K2.5Moonshot AI1484
9Qwen3.8-27BQwen1479
10Beam-1.0-501B-A23Breflection1475
11MiMo-V2.5Xiaomi MiMo1469
12MiniMax-M3MiniMax1468
13NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1468
14Hy3Tencent1467
15InklingThinking Machines1467
16LongCat-Flash-ChatMeituan LongCat1467
17Qwen3.5-397B-A17BQwen1463
18GLM-5Z.ai1462
19Mistral-Medium-3.5-128BMistral AI1461
20gemma-4-31B-itGoogle1459
21Mistral-Large-4-1T-A52BMistral AI1457
22Inkling-2-SmallThinking Machines1455
23GLM-4.7Z.ai1454
24MiniMax-M2.7MiniMax1453
25Inkling-SmallThinking Machines1451
26Mistral-Large-3-675B-Instruct-2512Mistral AI1449
27GLM-4.6Z.ai1449
28gemma-4-26B-A4B-itGoogle1447
29Qwen3-235B-A22B-Instruct-2507Qwen1445
30MiMo-V2-FlashXiaomi MiMo1443
31Qwen3-Next-80B-A3B-InstructQwen1440
32Qwen3-VL-235B-A22B-InstructQwen1438
33Qwen3.5-122B-A10BQwen1435
34Step-3.5-FlashStepFun1435
35GLM-4.5Z.ai1434
36NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1433
37Qwen3.5-27BQwen1427
38Qwen3-VL-235B-A22B-ThinkingQwen1425
39Qwen3-235B-A22B-Thinking-2507Qwen1425
40Hy3-previewTencent1421
41Muse-Glimmer-30Bmeta-models1418
42Qwen3-30B-A3B-Instruct-2507Qwen1416
43Qwen3-Coder-480B-A35B-InstructQwen1412
44Qwen3.5-35B-A3BQwen1410
45NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA1404
46Qwen3-235B-A22BQwen1398
47GLM-4.5-AirZ.ai1397
48granite-4.2-30bIBM Granite1395
49Qwen3-Next-80B-A3B-ThinkingQwen1391
50GLM-4.6VZ.ai1391
51Ling-flash-2.0inclusionAI1389
52GLM-4.7-FlashZ.ai1382
53NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA1381
54Trinity-Large-PreviewArcee AI1381
55MiniMax-M2.5MiniMax1381
56gpt-oss-120bOpenAI1380
57NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1378
58INTELLECT-3Prime Intellect1375
59granite-4.2-8bIBM Granite1374
60MiniMax-M2MiniMax1371
61granite-4.2-3bIBM Granite1358
62Qwen3-32BQwen1358
63Trinity-Large-ThinkingArcee AI1357
64GLM-4.5VZ.ai1348
65Olmo-3.1-32B-InstructAi21347
66Qwen3-30B-A3BQwen1337
67QwQ-32BQwen1333
68granite-4.1-8bIBM Granite1313
69gpt-oss-20bOpenAI1306
70Llama-4-Maverick-17B-128E-InstructMeta Llama1301
71Qwen2.5-72B-InstructQwen1292
72Llama-3.1-405B-InstructMeta Llama1291
73Llama-4-Scout-17B-16E-InstructMeta Llama1286
74Qwen2.5-Coder-32B-InstructQwen1276
75Llama-3.3-70B-InstructMeta Llama1268
76Llama-3.1-70B-InstructMeta Llama1260
77granite-4.0-h-smallIBM Granite1249
78Llama-3.1-8B-InstructMeta Llama1195
79granite-3.1-8b-instructIBM Granite1186
80Mixtral-8x22B-Instruct-v0.1Mistral AI1165
81QwQ-32B-PreviewQwen1155
82granite-3.1-2b-instructIBM Granite1149
83granite-3.0-8b-instructIBM Granite1112
84Llama-3.2-3B-InstructMeta Llama1098
85granite-3.0-2b-instructIBM Granite1090
86Llama-3.2-1B-InstructMeta Llama1070
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.