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)
#44	MiMo-V2-Pro medium	Xiaomi	7.5	7.6	1/2	94.2s
#46	Claude Sonnet 4.6 medium	Anthropic	6.9	7.6	1/2	33.9s
#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
#52	GPT-5.3 Chat none	OpenAI	6.9	7.4	1/2	10.5s
#53	MiMo-V2.5 medium	Xiaomi	6.9	7.4	1/2	64.5s
#54	Kimi K2.6 medium	Moonshot AI	6.5	7.4	1/2	118.2s
#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
#63	Claude Opus 4.6 medium	Anthropic	7.2	7.2	1/2	29.4s
#64	GPT-5.4 Nano medium	OpenAI	6.8	7.1	1/2	21.1s
#65	GPT-5.4 Mini medium	OpenAI	7.5	7.1	1/2	73.3s
#68	Seed-2.0-Mini medium	Bytedance Seed	6.8	7.1	1/2	220.5s
#69	Claude Sonnet 4.6 none	Anthropic	6.8	7.0	1/2	6.73s
#70	Qwen3.5-35B-A3B medium	Qwen	6.5	7.0	1/2	244.5s

Coding Ranking