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 ↑.
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) |
|---|---|---|---|---|---|---|---|
| #246 | Inkling Small none | Thinkingmachines | 1 | 5.3 | $0.054 | 5/22 | 1.51s |
| #247 | Laguna XS 2.1 none | Poolside | 1 | 5.3 | $0.008 | 5/22 | 1.55s |
| #250 | Gemini 3.1 Flash Lite Preview high | 1 | 5.3 | $2.310 | 13/16 | 68.1s | |
| #253 | Inkling none | Thinkingmachines | 1 | 5.2 | $0.147 | 6/22 | 3.47s |
| #254 | Granite 4.2 8B medium | IBM Granite | 1 | 5.2 | $0.009 | 7/22 | 46.0s |
| #256 | Mistral Small 4 none | Mistral | 1 | 5.1 | $0.022 | 5/22 | 1.20s |
| #258 | Granite 4.2 8B low | IBM Granite | 1 | 5.1 | $0.012 | 7/22 | 54.4s |
| #259 | Qwen3 Coder Next none | Qwen | 1 | 5.1 | $0.026 | 5/22 | 8.63s |
| #260 | MiMo-V2.5 none | Xiaomi | 1 | 5.1 | $0.025 | 5/22 | 4.68s |
| #266 | Laguna S 2.1 low | Poolside | 1 | 5.0 | $0.082 | 3/22 | 85.3s |
| #267 | DeepSeek V3.2 none | DeepSeek | 1 | 5.0 | $0.054 | 6/22 | 17.9s |
| #268 | GPT-4o-mini none | OpenAI | 1 | 5.0 | $0.010 | 5/22 | 1.92s |
| #270 | Mercury 2.5 Preview none | Inception | 1 | 4.9 | $0.018 | 4/22 | 3.51s |
| #280 | GLM 4.7 Flash none | Z.ai | 1 | 4.8 | $0.016 | 5/22 | 8.81s |
| #284 | Laguna M.1 medium | Poolside | 1 | 4.7 | $0.033 | 9/19 | 14.7s |