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)
#139	MiMo-V2.5 none	Xiaomi	6.8	4.8	1/2	3.74s
#133	MiniMax M2.7 medium	Minimax	6.7	5.0	1/2	54.7s
#36	Gemini 2.5 Flash medium	Google	6.6	7.7	1/2	54.6s
#100	Owl Alpha medium	Openrouter	6.6	5.8	1/2	19.1s
#116	Qwen3.6 Flash none	Qwen	6.6	5.5	1/2	2.34s
#30	Qwen3.6 35B A3B medium	Qwen	6.6	7.8	1/2	59.3s
#83	Qwen3.6 27B medium	Qwen	6.6	6.6	1/2	165.4s
#54	Kimi K2.6 medium	Moonshot AI	6.5	7.4	1/2	118.2s
#70	Qwen3.5-35B-A3B medium	Qwen	6.5	7.0	1/2	244.5s
#84	Laguna Xs.2 medium	Poolside	6.3	6.6	0/1	14.4s
#117	Grok 4.20 Beta none	X AI	5.5	5.5	0/1	1.14s
#146	Ling-2.6-1T none	Inclusionai	5.5	4.5	0/1	10.6s
#94	GPT-5 Nano medium	OpenAI	5.4	6.1	0/2	47.8s
#95	DeepSeek V4 Pro none	DeepSeek	5.4	6.0	0/2	8.27s
#147	GPT-5.4 Nano none	OpenAI	5.4	4.5	0/2	1.09s

Coding Ranking