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

6.1

Best Model

Failure Reasons

With failure reason Wrong answer337 With failure reason API error51 With failure reason No answer39 With failure reason Timed out27 With failure reason Did not follow instructions25 With failure reason Extra formatting25

289/289

Rank	Model	Company	Coding Score	Score	Total Cost	Tests Correct	Response Time (avg)
#58	Kimi K3 max	Moonshot AI	10.0	7.9	$3.467	3/3	325.8s
Total Tests 3 Wrong Tests 0 Total Cost $3.467 Response Time (avg) 325.8s
#68	Qwen3.8 27B medium	Qwen	10.0	7.8	~$0.058	3/3	40.5s
Total Tests 3 Wrong Tests 0 Total Cost ~$0.058 Response Time (avg) 40.5s
#72	GLM 5 medium	Z.ai	10.0	7.7	$0.228	3/3	74.3s
Total Tests 3 Wrong Tests 0 Total Cost $0.228 Response Time (avg) 74.3s
#94	LongCat 2.0 medium	Meituan	10.0	7.4	$0.499	3/3	455.0s
Total Tests 3 Wrong Tests 0 Total Cost $0.499 Response Time (avg) 455.0s

Coding Ranking