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: Metric ↑.

Models Shown

Average Coding Score

6.1

Best Model

Failure Reasons

With failure reason Wrong answer120 With failure reason No answer18 With failure reason Did not follow instructions16 With failure reason Timed out12 With failure reason Extra formatting7 With failure reason API error6

Rank	Model	Company	Coding Score	Score	Tests Correct	Response Time (avg)
#99	Seed-2.0-Lite none	Bytedance Seed	6.8	5.9	1/2	2.95s
#46	Claude Sonnet 4.6 medium	Anthropic	6.9	7.6	1/2	33.9s
#52	GPT-5.3 Chat none	OpenAI	6.9	7.4	1/2	10.5s
#53	MiMo-V2.5 medium	Xiaomi	6.9	7.4	1/2	64.5s
#4	Gemini 3.1 Pro Preview medium	Google	7.0	9.3	1/2	54.3s
#24	Gemini 3.5 Flash minimal	Google	7.0	7.9	1/2	3.39s
#25	Qwen3.5-27B medium	Qwen	7.0	7.9	1/2	123.9s
#106	Owl Alpha none	Openrouter	7.0	5.7	1/2	39.7s
#40	MiMo-V2.5-Pro medium	Xiaomi	7.0	7.6	1/2	81.7s
#21	Seed-2.0-Lite medium	Bytedance Seed	7.0	8.1	1/2	107.7s
#63	Claude Opus 4.6 medium	Anthropic	7.2	7.2	1/2	29.4s
#90	Mercury 2 medium	Inception	7.2	6.3	1/2	2.29s
#12	Gemini 3 Flash Preview low	Google	7.3	8.6	1/2	6.66s
#103	Qwen3.5-27B none	Qwen	7.3	5.8	1/2	1.98s
#28	GLM 5 Turbo medium	Z.ai	7.3	7.9	1/2	53.9s

Coding Ranking