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

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

#ModelScore
1Kimi-K3Moonshot AI1515
2GLM-5.3-FlashZ.ai1511
3DeepSeek-V4.1-FlashDeepSeek1503
4Kimi-K2.6Moonshot AI1492
5Kimi-K3.1-ProMoonshot AI1489
6Qwen3.8-27BQwen1479
7Inkling-2-SmallThinking Machines1478
8InklingThinking Machines1469
9Kimi-K2.5Moonshot AI1465
10gemma-4-31B-itGoogle1465
11Qwen3.5-397B-A17BQwen1462
12MiniMax-M3MiniMax1460
13MiMo-V2.5Xiaomi MiMo1460
14gemma-4-26B-A4B-itGoogle1448
15Mistral-Large-4-1T-A52BMistral AI1446
16Qwen3-VL-235B-A22B-InstructQwen1442
17Inkling-SmallThinking Machines1440
18Qwen3.5-122B-A10BQwen1431
19Qwen3-VL-235B-A22B-ThinkingQwen1429
20Qwen3.5-27BQwen1428
21NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1422
22Qwen3.5-35B-A3BQwen1408
23Muse-Glimmer-30Bmeta-models1388
24GLM-4.6VZ.ai1372
25GLM-4.5VZ.ai1351
26gemma-3-27b-itGoogle1303
27Llama-4-Maverick-17B-128E-InstructMeta Llama1258
28gemma-3-12b-itGoogle1247
29gemma-3n-E4B-itGoogle1246
30Llama-4-Scout-17B-16E-InstructMeta Llama1235
31gemma-3-4b-itGoogle1223
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.