Coding Model Ranking

AI BENCHY Category

See which AI models perform best on Coding, which ones stay reliable, and where the biggest gaps appear.

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
#6	Gemini 3.5 Flash medium	Google	6.8	9.0	1/2	9.91s
#64	GPT-5.4 Nano medium	OpenAI	6.8	7.1	1/2	21.1s
#68	Seed-2.0-Mini medium	Bytedance Seed	6.8	7.1	1/2	220.5s
#110	Kimi K2.6 none	Moonshot AI	6.8	5.6	1/2	122.8s
#3	Gemini 3.5 Flash low	Google	6.8	9.3	1/2	5.54s
#26	Qwen3.7 Max none	Qwen	6.8	7.9	1/2	1.39s
#34	Gemini 3.1 Flash Lite Preview medium	Google	6.8	7.7	1/2	3.98s
#35	Gemini 3.1 Flash Lite medium	Google	6.8	7.7	1/2	3.59s
#39	Gemini 3 Flash Preview none	Google	6.8	7.7	1/2	2.19s
#41	Gemini 3.1 Flash Lite Preview low	Google	6.8	7.6	1/2	1.56s
#49	Gemini 3.1 Flash Lite Preview none	Google	6.8	7.5	1/2	1.06s
#50	Gemini 3.1 Flash Lite low	Google	6.8	7.4	1/2	1.71s
#55	DeepSeek V4 Flash high	DeepSeek	6.8	7.4	1/2	58.1s
#60	GLM 5V Turbo medium	Z.ai	6.8	7.4	1/2	54.8s

Coding Ranking