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 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)
#113	GLM 5.1 none	Z.ai	4.3	5.6	0/2	6.33s
#104	Qwen3.6 27B none	Qwen	6.8	5.8	1/2	5.75s
#3	Gemini 3.5 Flash low	Google	6.8	9.3	1/2	5.54s
#142	Qwen3.5-9B none	Qwen	4.4	4.6	0/2	5.39s
#89	GLM 5 none	Z.ai	4.6	6.3	0/2	5.18s
#144	Hy3 preview none	Tencent	2.3	4.6	0/1	4.56s
#34	Gemini 3.1 Flash Lite Preview medium	Google	6.8	7.7	1/2	3.98s
#91	Gemma 4 26B A4B none	Google	4.1	6.2	0/2	3.83s
#98	GLM 5V Turbo none	Z.ai	6.8	5.9	1/2	3.77s
#139	MiMo-V2.5 none	Xiaomi	6.8	4.8	1/2	3.74s
#35	Gemini 3.1 Flash Lite medium	Google	6.8	7.7	1/2	3.59s
#24	Gemini 3.5 Flash minimal	Google	7.0	7.9	1/2	3.39s
#109	GLM 4.7 Flash none	Z.ai	5.0	5.6	0/2	3.35s
#66	Qwen3.6 Max Preview none	Qwen	4.2	7.1	0/2	3.06s
#134	Nemotron 3 Super none	NVIDIA	3.4	5.0	0/2	3.02s

Coding Ranking