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. Sort by: Failure Count ↑.
| Rank | Model | Company | Did not follow instructions Count | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #114 | Qwen3.5 Plus 2026-04-20 none | Qwen | 2 | 5.7 | 7/21 | 4.39s |
| #115 | Qwen3.5-27B none | Qwen | 2 | 5.7 | 7/21 | 1.68s |
| #116 | Hunter Alpha none | OpenRouter | 2 | 5.7 | 6/18 | 4.70s |
| #117 | Qwen3.5-35B-A3B none | Qwen | 2 | 5.6 | 7/21 | 3.37s |
| #118 | Qwen3.6 27B none | Qwen | 2 | 5.6 | 7/21 | 3.72s |
| #120 | Mimo V2 PRO none | Xiaomi | 2 | 5.6 | 7/21 | 2.27s |
| #126 | gpt-oss-120b none | OpenAI | 2 | 5.4 | 6/19 | 21.6s |
| #131 | Qwen3.5-122B-A10B none | Qwen | 2 | 5.3 | 6/21 | 3.41s |
| #132 | Mistral Small 4 medium | Mistral | 2 | 5.3 | 5/21 | 9.40s |
| #134 | GLM 5 Turbo none | Z.ai | 2 | 5.2 | 6/21 | 2.82s |
| #136 | Elephant Alpha medium | Openrouter | 2 | 5.1 | 6/21 | 1.27s |
| #138 | Ling-2.6-flash none | Inclusionai | 2 | 5.0 | 6/21 | 9.34s |
| #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 |