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

67 models in expert ranked by LMArena score · updated Nov 11, 2026

#ModelScore
1GLM-5.3Z.ai1519
2GLM-5.3-FlashZ.ai1511
3DeepSeek-V4.1-FlashDeepSeek1503
4MiMo-V2.5-ProXiaomi MiMo1502
5Kimi-K2.6Moonshot AI1492
6GLM-5.2Z.ai1488
7Qwen3.8-27BQwen1479
8Inkling-2-SmallThinking Machines1478
9GLM-5.1Z.ai1477
10NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1473
11InklingThinking Machines1469
12Kimi-K2.5Moonshot AI1465
13gemma-4-31B-itGoogle1465
14Beam-1.0-501B-A23Breflection1464
15Qwen3-235B-A22B-Thinking-2507Qwen1463
16Qwen3.5-397B-A17BQwen1462
17MiniMax-M3MiniMax1460
18MiMo-V2.5Xiaomi MiMo1460
19Hy3Tencent1458
20GLM-5Z.ai1455
21gemma-4-26B-A4B-itGoogle1448
22Mistral-Large-4-1T-A52BMistral AI1446
23MiniMax-M2.7MiniMax1443
24LongCat-Flash-ChatMeituan LongCat1441
25Inkling-SmallThinking Machines1440
26GLM-4.5Z.ai1433
27GLM-4.6Z.ai1433
28Mistral-Medium-3.5-128BMistral AI1431
29Qwen3.5-122B-A10BQwen1431
30Qwen3-VL-235B-A22B-ThinkingQwen1429
31Qwen3.5-27BQwen1428
32MiMo-V2-FlashXiaomi MiMo1426
33Hy3-previewTencent1424
34GLM-4.7Z.ai1424
35DeepSeek-V3.2-ExpDeepSeek1423
36Mistral-Large-3-675B-Instruct-2512Mistral AI1422
37NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1422
38Step-3.5-FlashStepFun1421
39granite-4.2-30bIBM Granite1408
40Qwen3.5-35B-A3BQwen1408
41DeepSeek-V3.1DeepSeek1405
42NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA1399
43DeepSeek-R1-0528DeepSeek1393
44Muse-Glimmer-30Bmeta-models1388
45granite-4.2-8bIBM Granite1381
46MiniMax-M2.5MiniMax1380
47Qwen3-Next-80B-A3B-ThinkingQwen1375
48GLM-4.6VZ.ai1372
49GLM-4.5-AirZ.ai1370
50Qwen3-235B-A22BQwen1369
51Qwen3-32BQwen1362
52NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA1360
53Trinity-Large-ThinkingArcee AI1359
54GLM-4.7-FlashZ.ai1358
55gpt-oss-120bOpenAI1355
56NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1355
57Ling-flash-2.0inclusionAI1353
58GLM-4.5VZ.ai1351
59MiniMax-M2MiniMax1340
60DeepSeek-R1DeepSeek1337
61QwQ-32BQwen1323
62INTELLECT-3Prime Intellect1323
63Qwen3-30B-A3BQwen1314
64granite-4.2-3bIBM Granite1305
65Olmo-3.1-32B-ThinkAi21294
66Olmo-3-32B-ThinkAi21273
67gpt-oss-20bOpenAI1259
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.