Coding Model Ranking

AI BENCHY Category

See which AI models perform best on Coding, which ones stay reliable, and where the biggest gaps appear.

Models Shown

Average Coding Score

6.1

Best Model

Failure Reasons

With failure reason Wrong answer120 With failure reason No answer18 With failure reason Did not follow instructions16 With failure reason Timed out12 With failure reason Extra formatting7 With failure reason API error6

Rank	Model	Company	Coding Score	Score	Tests Correct	Response Time (avg)
#51	GLM 5.1 medium	Z.ai	4.7	7.4	0/2	145.6s
#89	GLM 5 none	Z.ai	4.6	6.3	0/2	5.18s
#101	Qwen3.5 Plus 2026-04-20 none	Qwen	4.4	5.8	0/2	2.08s
#125	GLM 5 Turbo none	Z.ai	4.4	5.3	0/2	2.58s
#142	Qwen3.5-9B none	Qwen	4.4	4.6	0/2	5.39s
#74	Laguna M.1 medium	Poolside	4.3	6.9	0/1	35.6s
#129	gpt-oss-120b none	OpenAI	4.3	5.2	0/1	9.57s
#113	GLM 5.1 none	Z.ai	4.3	5.6	0/2	6.33s
#66	Qwen3.6 Max Preview none	Qwen	4.2	7.1	0/2	3.06s
#105	Cobuddy medium	Baidu	4.1	5.7	0/2	79.2s
#33	Qwen3.6 Plus medium	Qwen	4.1	7.8	0/2	201.7s
#38	Qwen3.5-122B-A10B medium	Qwen	4.1	7.7	0/2	119.6s
#56	Qwen3.5-Flash medium	Qwen	4.1	7.4	0/2	54.2s
#67	MiMo-V2-Flash medium	Xiaomi	4.1	7.1	0/2	7.20s
#91	Gemma 4 26B A4B none	Google	4.1	6.2	0/2	3.83s

Coding Ranking