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

32 models in instructions ranked by LMArena score · updated Nov 11, 2026

#ModelScore
1Kimi-K3Moonshot AI1484
2GLM-5.3-FlashZ.ai1480
3DeepSeek-V4.1-FlashDeepSeek1473
4Kimi-K3.1-ProMoonshot AI1472
5Kimi-K2.6Moonshot AI1451
6MiMo-V2.5Xiaomi MiMo1434
7gemma-4-31B-itGoogle1433
8Qwen3.8-27BQwen1431
9Kimi-K2.5Moonshot AI1431
10MiniMax-M3MiniMax1428
11InklingThinking Machines1427
12Qwen3.5-397B-A17BQwen1424
13gemma-4-26B-A4B-itGoogle1421
14Mistral-Large-4-1T-A52BMistral AI1409
15Inkling-2-SmallThinking Machines1408
16Qwen3-VL-235B-A22B-InstructQwen1406
17Inkling-SmallThinking Machines1402
18NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-BF16NVIDIA1400
19Qwen3.5-122B-A10BQwen1399
20Qwen3.5-27BQwen1392
Show all 32 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.