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: Tests Correct ↑.

Models Shown

Average Coding Score

5.7

Best Model

Failure Reasons

With failure reason Wrong answer230 With failure reason API error43 With failure reason Timed out25 With failure reason No answer18 With failure reason Did not follow instructions16 With failure reason Extra formatting12

189/189

Rank	Model	Company	Coding Score	Score	Total Cost	Tests Correct	Response Time (avg)
#19	GPT-5 Mini medium	OpenAI	10.0	8.5	$0.159	3/3	27.6s
Total Tests 3 Wrong Tests 0 Total Cost $0.159 Response Time (avg) 27.6s
#25	GPT-5.2 medium	OpenAI	10.0	8.4	$0.548	3/3	22.7s
Total Tests 3 Wrong Tests 0 Total Cost $0.548 Response Time (avg) 22.7s
#40	Grok 4.5 low	X AI	10.0	7.8	$0.760	3/3	13.7s
Total Tests 3 Wrong Tests 0 Total Cost $0.760 Response Time (avg) 13.7s
#62	Claude Opus 4.7 none	Anthropic	3.3	7.4	$0.505	1/1	2.84s
Total Tests 1 Wrong Tests 0 Total Cost $0.505 Response Time (avg) 2.84s
#83	Grok 4.20 Beta medium	X AI	3.3	6.8	$0.750	1/1	31.4s
Total Tests 1 Wrong Tests 0 Total Cost $0.750 Response Time (avg) 31.4s
#97	Gemini 3.1 Flash Lite high	Google	3.3	6.5	$2.044	1/1	137.6s
Total Tests 1 Wrong Tests 0 Total Cost $2.044 Response Time (avg) 137.6s
#156	Grok 4.20 Multi Agent Beta medium	X AI	3.3	5.0	$5.599	1/1	27.1s
Total Tests 1 Wrong Tests 0 Total Cost $5.599 Response Time (avg) 27.1s
#180	Grok Build 0.1 none	X AI	3.3	4.2	$0.547	1/1	21.4s
Total Tests 1 Wrong Tests 0 Total Cost $0.547 Response Time (avg) 21.4s
#187	Nemotron 3 Nano Omni 30b A3b Reasoning none	NVIDIA	3.3	3.5	$0.000	1/1	1.27s
Total Tests 1 Wrong Tests 0 Total Cost $0.000 Response Time (avg) 1.27s

Coding Ranking