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: Response Time (avg) ↓.

Models Shown

Average Coding Score

6.1

Best Model

Failure Reasons

With failure reason Wrong answer119 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)
#73	GPT-5 Mini medium	OpenAI	10.0	6.9	2/2	30.7s
#63	Claude Opus 4.6 medium	Anthropic	7.2	7.2	1/2	29.4s
#38	Hy3 preview low	Tencent	10.0	7.7	1/1	27.9s
#81	Grok 4.20 Multi Agent Beta medium	X AI	10.0	6.6	1/1	27.1s
#2	Gemini 3.5 Flash high	Google	10.0	9.6	2/2	24.6s
#131	DeepSeek V4 Flash none	DeepSeek	4.8	5.1	0/2	24.5s
#87	Grok 4.1 Fast medium	X AI	2.3	6.5	0/1	23.6s
#57	GPT-5.2 medium	OpenAI	10.0	7.4	2/2	23.2s
#5	Qwen3.7 Max medium	Qwen	10.0	9.0	2/2	23.0s
#82	Grok Build 0.1 none	X AI	10.0	6.6	1/1	21.4s
#64	GPT-5.4 Nano medium	OpenAI	6.8	7.1	1/2	21.1s
#114	DeepSeek V3.2 none	DeepSeek	3.1	5.6	0/2	20.9s
#100	Owl Alpha medium	Openrouter	6.6	5.8	1/2	19.1s
#15	GPT-5.3-Codex medium	OpenAI	10.0	8.3	2/2	18.5s
#76	Gemma 4 31B none	Google	6.8	6.7	1/2	14.8s

Coding Ranking