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)
#31	Grok 4.3 medium	X AI	7.4	7.8	1/2	55.3s
#123	Laguna M.1 none	Poolside	7.5	5.4	0/1	2.93s
#44	MiMo-V2-Pro medium	Xiaomi	7.5	7.6	1/2	94.2s
#65	GPT-5.4 Mini medium	OpenAI	7.5	7.1	1/2	73.3s
#20	Qwen3.5 Plus 2026-02-15 medium	Qwen	7.6	8.1	1/2	193.8s
#1	Gemini 3 Flash Preview medium	Google	7.9	9.8	1/2	96.0s
#9	Gemini 3.5 Flash none	Google	8.2	8.9	1/2	39.6s
#11	GPT-5.5 medium	OpenAI	8.2	8.7	1/2	69.7s
#14	Qwen3.6 Max Preview medium	Qwen	8.2	8.4	1/2	178.0s
#27	GPT-5.4 medium	OpenAI	8.2	7.9	1/2	55.0s
#43	GPT-5.2 Chat none	OpenAI	8.2	7.6	1/2	8.05s
#2	Gemini 3.5 Flash high	Google	10.0	9.6	2/2	24.6s
#5	Qwen3.7 Max medium	Qwen	10.0	9.0	2/2	23.0s
#7	Claude Opus 4.7 medium	Anthropic	10.0	8.9	2/2	14.8s
#8	GPT-5.5 low	OpenAI	10.0	8.9	2/2	14.4s

Coding Ranking