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) |
|---|---|---|---|---|---|---|
| #130 | MiniMax M2.7 medium | Minimax | 5 | 5.3 | 5/21 | 38.2s |
| #86 | Grok 4.1 Fast medium | X AI | 4 | 6.5 | 9/19 | 23.8s |
| #123 | MiMo-V2.5-Pro none | Xiaomi | 4 | 5.5 | 6/21 | 1.78s |
| #156 | Hy3 preview none | Tencent | 4 | 4.4 | 4/21 | 12.9s |
| #163 | Granite 4.1 8B none | IBM Granite | 4 | 4.0 | 2/21 | 728ms |
| #42 | GPT-5.2 medium | OpenAI | 3 | 7.5 | 13/21 | 16.9s |
| #45 | GPT-5.4 Mini medium | OpenAI | 3 | 7.5 | 12/21 | 22.3s |
| #53 | Gemini 3.1 Flash Lite high | 3 | 7.3 | 10/18 | 62.0s | |
| #54 | GPT-5 Mini medium | OpenAI | 3 | 7.3 | 12/21 | 23.6s |
| #62 | Step 3.5 Flash medium | Stepfun | 3 | 7.2 | 11/20 | 72.5s |
| #81 | Mercury 2 medium | Inception | 3 | 6.6 | 10/21 | 2.24s |
| #87 | Gemini 3.1 Flash Lite minimal | 3 | 6.4 | 10/21 | 1.33s | |
| #99 | gpt-oss-120b medium | OpenAI | 3 | 6.1 | 9/21 | 22.3s |
| #105 | Nemotron 3 Super medium | NVIDIA | 3 | 5.8 | 8/21 | 32.0s |
| #119 | Cobuddy medium | Baidu | 3 | 5.6 | 7/21 | 39.9s |