Coding Model Ranking

AI BENCHY Category

See which AI models perform best on Coding, which ones stay reliable, and where the biggest gaps appear. Sort by: Response Time (avg) ↑.

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)
#112	GPT-5.4 none	OpenAI	6.8	5.6	1/2	1.99s
#132	Qwen3 Coder Next none	Qwen	5.4	5.1	0/2	2.01s
#149	MiMo-V2-Flash none	Xiaomi	4.9	4.4	0/2	2.04s
#138	GPT-4o-mini none	OpenAI	3.2	4.9	0/2	2.05s
#101	Qwen3.5 Plus 2026-04-20 none	Qwen	4.4	5.8	0/2	2.08s
#124	Qwen3.5-122B-A10B none	Qwen	4.0	5.4	0/2	2.14s
#39	Gemini 3 Flash Preview none	Google	6.8	7.7	1/2	2.19s
#90	Mercury 2 medium	Inception	7.2	6.3	1/2	2.29s
#116	Qwen3.6 Flash none	Qwen	6.6	5.5	1/2	2.34s
#88	Qwen3.5 Plus 2026-02-15 none	Qwen	4.9	6.4	0/2	2.54s
#125	GLM 5 Turbo none	Z.ai	4.4	5.3	0/2	2.58s
#107	MiMo-V2-Pro none	Xiaomi	6.8	5.7	1/2	2.65s
#93	MiMo-V2-Omni none	Xiaomi	5.1	6.2	0/2	2.75s
#10	Claude Opus 4.7 none	Anthropic	10.0	8.9	1/1	2.84s
#123	Laguna M.1 none	Poolside	7.5	5.4	0/1	2.93s

Coding Ranking