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)
#179	MiMo-V2-Flash none	Xiaomi	4.3	4.3	$0.025	0/3	2.64s
Total Tests 3 Wrong Tests 3 Total Cost $0.025 Response Time (avg) 2.64s
#181	Grok 4.1 Fast none	X AI	1.8	4.0	$0.008	0/1	1.79s
Total Tests 1 Wrong Tests 1 Total Cost $0.008 Response Time (avg) 1.79s
#182	Laguna Xs.2 none	Poolside	8.3	4.0	$0.004	0/1	1.96s
Total Tests 1 Wrong Tests 1 Total Cost $0.004 Response Time (avg) 1.96s
#183	Granite 4.1 8B none	IBM Granite	4.5	4.0	$0.003	0/3	775ms
Total Tests 3 Wrong Tests 3 Total Cost $0.003 Response Time (avg) 775ms
#184	gpt-oss-120b none	OpenAI	1.5	4.0	$0.010	0/1	9.57s
Total Tests 1 Wrong Tests 1 Total Cost $0.010 Response Time (avg) 9.57s
#185	Qwen3.5-9B medium	Qwen	2.9	3.8	$0.036	0/3	100.9s
Total Tests 3 Wrong Tests 3 Total Cost $0.036 Response Time (avg) 100.9s
#186	Nemotron 3 Nano Omni 30b A3b Reasoning medium	NVIDIA	1.1	3.6	$0.000	0/1	38.1s
Total Tests 1 Wrong Tests 1 Total Cost $0.000 Response Time (avg) 38.1s
#188	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
#189	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