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 ↑.
Categories
293/293
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) |
|---|---|---|---|---|---|---|---|
| #351 | MiniMax M2.7 medium | Minimax | 5 | 0.5 | $0.326 | 5/23 | 50.3s |
| #353 | GPT-4o-mini default | OpenAI | 1 | 0.5 | $0.024 | 5/23 | 4.16s |
| #356 | Inkling Small none | Thinkingmachines | 1 | 0.5 | $0.054 | 5/23 | 1.45s |
| #357 | Qwen3 Coder Next default | Qwen | 1 | 0.5 | $0.067 | 5/23 | 19.7s |
| #361 | MiMo-V2.5 none | Xiaomi | 1 | 0.5 | $0.049 | 5/23 | 9.88s |
| #366 | GLM 4.7 Flash none | Z.ai | 1 | 0.5 | $0.027 | 5/23 | 13.0s |
| #368 | Nemotron 3.5 Lightning medium | NVIDIA | 3 | 0.5 | $0.195 | 5/23 | 81.9s |
| #378 | Nemotron 3.5 Lightning low | NVIDIA | 2 | 0.5 | $0.175 | 5/23 | 83.2s |
| #386 | Nemotron 3 Super none | NVIDIA | 2 | 0.4 | $0.016 | 5/23 | 7.11s |
| #393 | MiniMax M2.5 medium | Minimax | 3 | 0.4 | $0.440 | 5/23 | 102.3s |
| #413 | Elephant Alpha default | Openrouter | 3 | 0.4 | $0.000 | 5/21 | 1.22s |
| #436 | GPT-6 Luna Decisions default | OpenAI | 1 | 0.2 | $0.005 | 3/12 | 495ms |
| #301 | Trinity Large Thinking high | Arcee AI | 4 | 0.6 | $0.794 | 6/23 | 74.5s |
| #303 | GPT-5.4 Mini none | OpenAI | 3 | 0.6 | $0.170 | 6/23 | 3.34s |
| #304 | Mistral Large 4 none | Mistral | 1 | 0.6 | $0.290 | 6/23 | 20.4s |