Coding Model Ranking

See which AI models perform best on Coding, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.

Models Shown

Average Coding Score

0.6

Best Model

Gemini 3.1 Flash Lite Preview 0.0

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)
#158	Qwen3.6 27B medium	Qwen	0.8	0.7	$1.021	2/3	143.0s
Total Tests 3 Wrong Tests 1 Total Cost $1.021 Response Time (avg) 143.0s
#205	Qwen3.6 35B A3B medium	Qwen	0.8	0.7	$0.834	2/3	50.5s
Total Tests 3 Wrong Tests 1 Total Cost $0.834 Response Time (avg) 50.5s
#145	Gemini 2.5 Flash medium	Google	0.8	0.7	$0.680	2/3	41.0s
Total Tests 3 Wrong Tests 1 Total Cost $0.680 Response Time (avg) 41.0s
#368	Grok 4.1 Fast medium	X AI	0.8	0.4	$0.069	0/1	23.6s
Total Tests 1 Wrong Tests 1 Total Cost $0.069 Response Time (avg) 23.6s
#43	Claude Opus 5 low	Anthropic	0.8	0.9	$2.350	2/3	6.70s
Total Tests 3 Wrong Tests 1 Total Cost $2.350 Response Time (avg) 6.70s
#118	GPT-6 Luna high	OpenAI	0.8	0.8	$0.074	2/3	24.7s
Total Tests 3 Wrong Tests 1 Total Cost $0.074 Response Time (avg) 24.7s
#39	Gemini 3.5 Flash low	Google	0.8	0.9	$0.752	2/3	6.71s
Total Tests 3 Wrong Tests 1 Total Cost $0.752 Response Time (avg) 6.71s
#44	Gemini 3.6 Flash low	Google	0.8	0.9	$0.363	2/3	6.95s
Total Tests 3 Wrong Tests 1 Total Cost $0.363 Response Time (avg) 6.95s
#94	DeepSeek V4 Flash 0423 high	DeepSeek	0.8	0.8	$0.261	2/3	50.6s
Total Tests 3 Wrong Tests 1 Total Cost $0.261 Response Time (avg) 50.6s
#182	Mercury 2.5 Preview medium	Inception	0.8	0.7	$0.039	2/3	3.86s
Total Tests 3 Wrong Tests 1 Total Cost $0.039 Response Time (avg) 3.86s
#203	KAT-Coder-Pro V2.5 low	Kwaipilot	0.8	0.7	$0.568	2/3	24.9s
Total Tests 3 Wrong Tests 1 Total Cost $0.568 Response Time (avg) 24.9s
#239	KAT-Coder-Pro V2.5 medium	Kwaipilot	0.8	0.6	$0.669	2/3	33.1s
Total Tests 3 Wrong Tests 1 Total Cost $0.669 Response Time (avg) 33.1s
#255	Inkling Small medium	Thinkingmachines	0.8	0.6	$0.113	2/3	10.5s
Total Tests 3 Wrong Tests 1 Total Cost $0.113 Response Time (avg) 10.5s
#71	Qwen3.8 2.4T A95B low	Qwen	0.8	0.8	$4.016	2/3	172.5s
Total Tests 3 Wrong Tests 1 Total Cost $4.016 Response Time (avg) 172.5s
#146	LongCat 2.0 high	Meituan	0.8	0.7	$0.778	2/3	505.3s
Total Tests 3 Wrong Tests 1 Total Cost $0.778 Response Time (avg) 505.3s

Coding Ranking

Filter models

Top Models by Coding Score

Coding Score vs Total Cost

Top Models by Response Time (avg)