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)
#99	Seed-2.0-Lite none	Bytedance Seed	6.8	5.9	1/2	2.95s
#134	Nemotron 3 Super none	NVIDIA	3.4	5.0	0/2	3.02s
#66	Qwen3.6 Max Preview none	Qwen	4.2	7.1	0/2	3.06s
#109	GLM 4.7 Flash none	Z.ai	5.0	5.6	0/2	3.35s
#24	Gemini 3.5 Flash minimal	Google	7.0	7.9	1/2	3.39s
#35	Gemini 3.1 Flash Lite medium	Google	6.8	7.7	1/2	3.59s
#139	MiMo-V2.5 none	Xiaomi	6.8	4.8	1/2	3.74s
#98	GLM 5V Turbo none	Z.ai	6.8	5.9	1/2	3.77s
#91	Gemma 4 26B A4B none	Google	4.1	6.2	0/2	3.83s
#34	Gemini 3.1 Flash Lite Preview medium	Google	6.8	7.7	1/2	3.98s
#144	Hy3 preview none	Tencent	2.3	4.6	0/1	4.56s
#89	GLM 5 none	Z.ai	4.6	6.3	0/2	5.18s
#142	Qwen3.5-9B none	Qwen	4.4	4.6	0/2	5.39s
#3	Gemini 3.5 Flash low	Google	6.8	9.3	1/2	5.54s
#104	Qwen3.6 27B none	Qwen	6.8	5.8	1/2	5.75s

Coding Ranking