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

68 models in coding ranked by LMArena score · updated Nov 11, 2026

#ModelScore
68Olmo-3.1-32B-ThinkAi21290
67gpt-oss-20bOpenAI1306
66Olmo-3-32B-ThinkAi21318
65QwQ-32BQwen1333
64Qwen3-30B-A3BQwen1337
63GLM-4.5VZ.ai1348
62Trinity-Large-ThinkingArcee AI1357
61Qwen3-32BQwen1358
60granite-4.2-3bIBM Granite1358
59MiniMax-M2MiniMax1371
58DeepSeek-R1DeepSeek1371
57granite-4.2-8bIBM Granite1374
56INTELLECT-3Prime Intellect1375
55NVIDIA-Nemotron-3-Nano-30B-A3B-BF16NVIDIA1378
54gpt-oss-120bOpenAI1380
53MiniMax-M2.5MiniMax1381
52NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16NVIDIA1381
51GLM-4.7-FlashZ.ai1382
50Ling-flash-2.0inclusionAI1389
49GLM-4.6VZ.ai1391
Show all 68 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.