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: Tests Correct ↓.
215/215
Filter models
No models match the current search and filters.
| Rank | Model | Company | Did not follow instructions Count | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #208 | Dots 3 Note Preview medium | Dots Studio | 2 | 5.9 | $0.000 | 8/22 | 67.1s |
| #217 | Nemotron 3 Super medium | NVIDIA | 3 | 5.7 | $0.050 | 8/22 | 52.3s |
| #231 | KAT-Coder-Air V2.5 medium | Kwaipilot | 1 | 5.6 | $0.048 | 8/22 | 8.65s |
| #229 | Mimo V2 PRO none | Xiaomi | 2 | 5.6 | $0.045 | 7/21 | 2.27s |
| #230 | Owl Alpha none | Openrouter | 3 | 5.6 | $0.000 | 7/21 | 9.88s |
| #285 | Cobuddy medium | Baidu | 3 | 4.7 | $0.000 | 7/21 | 39.9s |
| #291 | Grok 4.20 Beta none | X AI | 1 | 4.4 | $0.087 | 6/18 | 1.19s |
| #297 | Hunter Alpha none | OpenRouter | 2 | 4.2 | $0.000 | 6/18 | 4.70s |
| #186 | Claude Sonnet 5 none | Anthropic | 1 | 6.1 | $0.548 | 7/22 | 6.05s |
| #190 | Qwen3.7 Flash none | Qwen | 1 | 6.1 | $0.019 | 7/22 | 10.1s |
| #195 | Qwen3.6 Flash none | Qwen | 1 | 6.1 | $0.062 | 7/22 | 3.73s |
| #214 | GPT-5.4 none | OpenAI | 1 | 5.8 | $0.397 | 7/22 | 2.08s |
| #234 | Qwen3.6 27B none | Qwen | 2 | 5.5 | $0.062 | 7/22 | 10.6s |
| #240 | KAT-Coder-Air V2.5 low | Kwaipilot | 2 | 5.4 | $0.046 | 7/22 | 10.6s |
| #254 | Granite 4.2 8B medium | IBM Granite | 1 | 5.2 | $0.009 | 7/22 | 46.0s |