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

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

#ModelScore
28Llama-4-Scout-17B-16E-InstructMeta Llama1255
27Llama-4-Maverick-17B-128E-InstructMeta Llama1278
26gemma-3n-E4B-itGoogle1309
25GLM-4.5VZ.ai1337
24gemma-3-27b-itGoogle1346
23Muse-Glimmer-30Bmeta-models1410
22GLM-4.6VZ.ai1424
21Qwen3-VL-235B-A22B-ThinkingQwen1442
20NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1451
19Qwen3.5-35B-A3BQwen1457
18Mistral-Large-4-1T-A52BMistral AI1457
17Qwen3-VL-235B-A22B-InstructQwen1462
16Inkling-SmallThinking Machines1462
15Qwen3.5-122B-A10BQwen1463
14MiniMax-M3MiniMax1465
13MiMo-V2.5Xiaomi MiMo1470
12gemma-4-31B-itGoogle1476
11Qwen3.5-27BQwen1479
10Qwen3.8-27BQwen1493
9Kimi-K2.5Moonshot AI1493
Show all 28 models

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.