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

63 models in math ranked by LMArena score · updated Nov 11, 2026

#ModelScore
1GLM-5.3-FlashZ.ai1503
2GLM-5.3Z.ai1500
3GLM-5.2Z.ai1483
4InklingThinking Machines1481
5MiMo-V2.5-ProXiaomi MiMo1481
6DeepSeek-V4.1-FlashDeepSeek1479
7Hy3Tencent1477
8Kimi-K2.6Moonshot AI1475
9GLM-5.1Z.ai1472
10gemma-4-26B-A4B-itGoogle1470
11Kimi-K2.5Moonshot AI1469
12gemma-4-31B-itGoogle1462
13Beam-1.0-501B-A23Breflection1459
14Inkling-SmallThinking Machines1459
15NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16NVIDIA1456
16Mistral-Large-4-1T-A52BMistral AI1456
17Qwen3.8-27BQwen1455
18Qwen3.5-397B-A17BQwen1453
19LongCat-Flash-ChatMeituan LongCat1441
20GLM-5Z.ai1439
21MiMo-V2.5Xiaomi MiMo1436
22GLM-4.6Z.ai1432
23Qwen3.5-122B-A10BQwen1431
24Mistral-Medium-3.5-128BMistral AI1430
25Qwen3.5-27BQwen1429
26GLM-4.5Z.ai1428
27Hy3-previewTencent1424
28MiniMax-M3MiniMax1423
29GLM-4.7Z.ai1423
30MiniMax-M2.7MiniMax1422
31DeepSeek-V3.2-ExpDeepSeek1420
32DeepSeek-V3.1DeepSeek1420
33Mistral-Large-3-675B-Instruct-2512Mistral AI1416
34Qwen3-235B-A22B-Thinking-2507Qwen1414
35NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1413
36Muse-Glimmer-30Bmeta-models1412
37Qwen3-VL-235B-A22B-ThinkingQwen1410
38Step-3.5-FlashStepFun1406
39Qwen3.5-35B-A3BQwen1403
40DeepSeek-V3.1-TerminusDeepSeek1402
41DeepSeek-R1-0528DeepSeek1400
42Qwen3-32BQwen1399
43Qwen3-Next-80B-A3B-ThinkingQwen1398
44Qwen3-235B-A22BQwen1397
45GLM-4.5-AirZ.ai1396
46MiMo-V2-FlashXiaomi MiMo1395
47DeepSeek-R1DeepSeek1393
48gpt-oss-120bOpenAI1389
49NVIDIA-Nemotron-3-Super-120B-A12B-BF16NVIDIA1379
50MiniMax-M2.5MiniMax1377
51INTELLECT-3Prime Intellect1376
52NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1370
53NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA1366
54Trinity-Large-ThinkingArcee AI1365
55Ling-flash-2.0inclusionAI1365
56QwQ-32BQwen1359
57GLM-4.7-FlashZ.ai1355
58Qwen3-30B-A3BQwen1355
59GLM-4.5VZ.ai1354
60MiniMax-M2MiniMax1353
61gpt-oss-20bOpenAI1317
62Olmo-3-32B-ThinkAi21315
63Olmo-3.1-32B-ThinkAi21305
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.