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 answer119 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)
#74	Grok 4.20 medium	X AI	4.1	7.0	0/2	65.1s
#56	MiMo-V2.5 medium	Xiaomi	6.9	7.4	1/2	64.5s
#58	Step 3.5 Flash medium	Stepfun	3.0	7.4	0/1	62.8s
#42	Grok Build 0.1 medium	X AI	7.0	7.7	1/2	62.6s
#96	Nemotron 3 Super medium	NVIDIA	3.1	5.9	0/2	62.4s
#64	Ring-2.6-1T medium	Inclusionai	10.0	7.2	1/1	59.6s
#32	Qwen3.6 35B A3B medium	Qwen	6.6	7.8	1/2	59.3s
#44	DeepSeek V4 Flash high	DeepSeek	6.8	7.6	1/2	58.1s
#149	GLM 4.7 Flash medium	Z.ai	3.4	4.5	0/2	55.3s
#33	Grok 4.3 medium	X AI	7.4	7.8	1/2	55.3s
#28	GPT-5.4 medium	OpenAI	8.2	7.9	1/2	55.0s
#59	GLM 5V Turbo medium	Z.ai	6.8	7.4	1/2	54.8s
#123	MiniMax M2.7 medium	Minimax	6.7	5.4	1/2	54.7s
#38	Gemini 2.5 Flash medium	Google	6.6	7.7	1/2	54.6s
#4	Gemini 3.1 Pro Preview medium	Google	7.0	9.3	1/2	54.3s

Coding Ranking