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: Tests Correct ↑.

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)
#10	Claude Opus 4.7 none	Anthropic	10.0	8.9	1/1	2.84s
#15	GPT-5.3-Codex medium	OpenAI	10.0	8.3	2/2	18.5s
#17	Grok 4.20 Beta medium	X AI	10.0	8.2	1/1	31.4s
#18	GLM 5 medium	Z.ai	10.0	8.2	2/2	89.5s
#22	Hy3 preview high	Tencent	10.0	8.0	1/1	99.8s
#29	Hy3 preview medium	Tencent	10.0	7.8	1/1	31.4s
#37	Hy3 preview low	Tencent	10.0	7.7	1/1	27.9s
#48	Gemini 3.1 Flash Lite high	Google	10.0	7.5	1/1	137.6s
#57	GPT-5.2 medium	OpenAI	10.0	7.4	2/2	23.2s
#61	Ring-2.6-1T medium	Inclusionai	10.0	7.2	1/1	59.6s
#62	Ring-2.6-1T none	Inclusionai	10.0	7.2	1/1	143.8s
#73	GPT-5 Mini medium	OpenAI	10.0	6.9	2/2	30.7s
#81	Grok 4.20 Multi Agent Beta medium	X AI	10.0	6.6	1/1	27.1s
#82	Grok Build 0.1 none	X AI	10.0	6.6	1/1	21.4s
#128	Ling-2.6-flash none	Inclusionai	10.0	5.3	1/1	11.2s

←

1 9 10 11

→

Coding Ranking