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

5.7

Best Model

Failure Reasons

With failure reason Wrong answer230 With failure reason API error43 With failure reason Timed out23 With failure reason No answer18 With failure reason Did not follow instructions16 With failure reason Extra formatting12

188/188

Rank	Model	Company	Coding Score	Score	Total Cost	Tests Correct	Response Time (avg)
#141	Laguna XS 2.1 none	Poolside	4.3	5.3	$0.003	0/3	623ms
Total Tests 3 Wrong Tests 3 Total Cost $0.003 Response Time (avg) 623ms
#105	Gemini 3 PRO Preview medium	Google	3.0	6.2	$0.385	0/3	0ms
Total Tests 3 Wrong Tests 3 Total Cost $0.385 Response Time (avg) 0ms
#110	Gemini 3.1 Flash Lite Preview high	Google	0.0	6.1	$2.310	0/0	0ms
Total Tests 0 Wrong Tests 0 Total Cost $2.310 Response Time (avg) 0ms
#129	Qwen3.6 Plus Preview medium	Qwen	9.8	5.8	$0.000	0/1	0ms
Total Tests 1 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 0ms
#151	Hunter Alpha medium	OpenRouter	9.8	5.1	$0.000	0/1	0ms
Total Tests 1 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 0ms
#173	Hunter Alpha none	OpenRouter	9.8	4.5	$0.000	0/1	0ms
Total Tests 1 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 0ms
#187	Step 3.5 Flash none	Stepfun	9.8	2.6	$0.020	0/1	0ms
Total Tests 1 Wrong Tests 1 Total Cost $0.020 Response Time (avg) 0ms
#188	LFM2-24B-A2B none	Liquid	0.0	2.4	$0.001	0/0	0ms
Total Tests 0 Wrong Tests 0 Total Cost $0.001 Response Time (avg) 0ms

Coding Ranking