Coding Model Ranking

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

0.6

Best Model

Gemini 3.6 Flash 1.0

Failure Reasons

With failure reason Wrong answer456 With failure reason API error64 With failure reason Did not follow instructions41 With failure reason No answer41 With failure reason Extra formatting36 With failure reason Timed out24

404/404

Rank	Model	Company	Coding Score	Score	Total Cost	Tests Correct	Response Time (avg)
#66	Grok 4.6 high	X AI	1.0	0.9	$2.629	3/3	102.2s
Total Tests 3 Wrong Tests 0 Total Cost $2.629 Response Time (avg) 102.2s
#69	Qwen3.7 Max medium	Qwen	1.0	0.9	$1.689	3/3	35.3s
Total Tests 3 Wrong Tests 0 Total Cost $1.689 Response Time (avg) 35.3s
#70	Claude Haiku 5.5 max	Anthropic	1.0	0.8	$0.509	3/3	55.9s
Total Tests 3 Wrong Tests 0 Total Cost $0.509 Response Time (avg) 55.9s
#72	GPT-5 Mini medium	OpenAI	1.0	0.8	$0.315	3/3	27.6s
Total Tests 3 Wrong Tests 0 Total Cost $0.315 Response Time (avg) 27.6s
#73	Muse Glimmer 30B xhigh	Meta	1.0	0.8	$0.585	3/3	105.9s
Total Tests 3 Wrong Tests 0 Total Cost $0.585 Response Time (avg) 105.9s
#76	Muse Spark 1.1 high	Meta	1.0	0.8	$2.570	3/3	22.9s
Total Tests 3 Wrong Tests 0 Total Cost $2.570 Response Time (avg) 22.9s
#81	Gemini 3.5 Flash high	Google	1.0	0.8	$2.737	3/3	23.0s
Total Tests 3 Wrong Tests 0 Total Cost $2.737 Response Time (avg) 23.0s
#82	Kimi K3 max	Moonshot AI	1.0	0.8	$3.409	3/3	325.8s
Total Tests 3 Wrong Tests 0 Total Cost $3.409 Response Time (avg) 325.8s
#84	Claude Opus 4.8 medium	Anthropic	1.0	0.8	$3.490	3/3	15.3s
Total Tests 3 Wrong Tests 0 Total Cost $3.490 Response Time (avg) 15.3s
#85	Ling 3.1 Flash medium	Inclusionai	1.0	0.8	$0.000	3/3	87.1s
Total Tests 3 Wrong Tests 0 Total Cost $0.000 Response Time (avg) 87.1s
#87	Grok 4.5 high	X AI	1.0	0.8	$2.687	3/3	155.2s
Total Tests 3 Wrong Tests 0 Total Cost $2.687 Response Time (avg) 155.2s
#95	DeepSeek V4.1 Flash low	DeepSeek	1.0	0.8	$0.494	3/3	40.7s
Total Tests 3 Wrong Tests 0 Total Cost $0.494 Response Time (avg) 40.7s
#100	Qwen3.8 Flash Next low	Qwen	1.0	0.8	~$0.045	3/3	29.5s
Total Tests 3 Wrong Tests 0 Total Cost ~$0.045 Response Time (avg) 29.5s
#116	Grok 4.5 low	X AI	1.0	0.8	$1.345	3/3	13.7s
Total Tests 3 Wrong Tests 0 Total Cost $1.345 Response Time (avg) 13.7s
#124	Qwen3.8 Flash Next medium	Qwen	1.0	0.8	~$0.047	3/3	45.5s
Total Tests 3 Wrong Tests 0 Total Cost ~$0.047 Response Time (avg) 45.5s

Coding Ranking

Filter models

Top Models by Coding Score

Coding Score vs Total Cost

Top Models by Response Time (avg)

Coding Ranking

Filter models

Top Models by Coding Score

Coding Score vs Total CostEstimated GPU electricity cost only. It excludes the rest of the computer and hardware ownership. NVIDIA GeForce RTX 3090: 0.4535 h × 0.300 kW × €0.2896/kWh × 1.138 USD/EUR = ~$0.044834.

Top Models by Response Time (avg)

Coding Score vs Total Cost