AI BENCHY Failures
Did not follow instructions Failures
See which AI models run into Did not follow instructions most often, so you can spot reliability risks before choosing one.
| Rank | Model | Company | Did not follow instructions Count | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #141 | Nemotron 3 Super none | NVIDIA | 2 | 4.9 | 5/21 | 5.30s |
| #148 | GPT-5.4 Nano none | OpenAI | 2 | 4.7 | 4/21 | 1.48s |
| #152 | MiMo-V2-Flash none | Xiaomi | 2 | 4.6 | 4/21 | 2.76s |
| #153 | Qwen3.6 35B A3B none | Qwen | 2 | 4.6 | 4/21 | 3.73s |
| #154 | Qwen3.5-9B none | Qwen | 2 | 4.6 | 4/21 | 1.89s |
| #158 | GLM 4.7 Flash medium | Z.ai | 2 | 4.4 | 4/21 | 35.1s |
| #159 | Ling-2.6-1T none | Inclusionai | 2 | 4.3 | 3/21 | 7.72s |
| #162 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 2 | 4.1 | 2/19 | 728ms |
| #7 | Gemini 3.5 Flash medium | 1 | 9.0 | 18/21 | 4.94s | |
| #12 | Gemini 3.1 Flash Lite Preview high | 1 | 8.6 | 13/16 | 68.1s | |
| #13 | Grok 4.20 Beta medium | X AI | 1 | 8.5 | 14/18 | 9.75s |
| #17 | GLM 5 medium | Z.ai | 1 | 8.3 | 15/21 | 33.5s |
| #22 | Step 3.7 Flash medium | Stepfun | 1 | 8.0 | 14/21 | 20.4s |
| #23 | GLM 5 Turbo medium | Z.ai | 1 | 8.0 | 14/21 | 23.0s |
| #24 | GPT-5.2 Chat none | OpenAI | 1 | 7.9 | 14/21 | 7.13s |