AI BENCHY
Advertise here

AI BENCHY Category Failures

General Intelligence: Did not follow instructions

General Intelligence
Did not follow instructions

See which AI models are most likely to hit Did not follow instructions on General Intelligence, so you can spot weak points faster. Sort by: Response Time (avg) ↓.

Models Shown

15

Total Failures

74

Most Affected Model

Qwen3.5-27B 1
Rank Model Company Did not follow instructions Count Category Score Tests Correct Response Time (avg)
#77 Claude Sonnet 4.6 none Anthropic 1 6.1 0/1 2.56s
#115 Qwen3.5-27B none Qwen 1 5.0 0/1 2.51s
#120 Mimo V2 PRO none Xiaomi 1 4.3 0/1 2.44s
#109 GLM 5V Turbo none Z.ai 1 4.6 0/1 2.22s
#134 GLM 5 Turbo none Z.ai 1 4.2 0/1 2.18s
#132 Mistral Small 4 medium Mistral 1 4.8 0/1 2.05s
#63 GPT-5.3 Chat none OpenAI 1 4.6 0/1 1.99s
#144 GPT-5.4 Mini none OpenAI 1 4.8 0/1 1.82s
#152 MiMo-V2-Flash none Xiaomi 1 4.6 0/1 1.67s
#124 Kimi K2.6 none Moonshot AI 1 5.4 0/1 1.55s
#50 Gemini 3.1 Flash Lite Preview low Google 1 4.0 0/1 1.54s
#114 Qwen3.5 Plus 2026-04-20 none Qwen 1 4.8 0/1 1.41s
#150 Qwen3 Coder Next medium Qwen 1 6.3 0/1 1.39s
#88 Qwen3.7 Plus none Qwen 1 5.3 0/1 1.33s
#148 GPT-5.4 Nano none OpenAI 1 3.8 0/1 1.31s

Top Models by Did not follow instructions Count

Did not follow instructions Count vs Score

Top Models by Response Time (avg)

Top Models by Estimated Wasted Cost