Anti-AI Tricks: Did not follow instructions
Anti-AI Tricks
Did not follow instructions
See which AI models are most likely to hit Did not follow instructions on Anti-AI Tricks, so you can spot weak points faster. Sort by: Tests Correct ↑.
Failure Reasons
43/43
Filter models
No models match the current search and filters.
| Rank | Model | Company | Did not follow instructions Count | Category Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #306 | GLM 4.7 Flash medium | Z.ai | 1 | 4.7 | $0.168 | 1/4 | 15.0s |
| #308 | Granite 4.2 8B none | IBM Granite | 1 | 4.9 | $0.037 | 1/4 | 17.8s |
| #312 | Hy3 preview none | Tencent | 2 | 4.8 | $0.007 | 1/4 | 11.1s |
| #315 | Granite 4.1 8B none | IBM Granite | 1 | 4.9 | $0.007 | 1/4 | 844ms |
| #45 | Muse Spark 1.2 high | Meta | 2 | 7.1 | $1.771 | 2/4 | 6.00s |
| #46 | Muse Spark 1.2 medium | Meta | 1 | 7.3 | $1.339 | 2/4 | 5.38s |
| #59 | GPT-5.2 medium | OpenAI | 1 | 6.5 | $1.182 | 2/4 | 7.81s |
| #70 | GPT-5 Mini medium | OpenAI | 1 | 7.1 | $0.241 | 2/4 | 13.9s |
| #73 | Muse Spark 1.1 high | Meta | 1 | 7.5 | $2.253 | 2/4 | 8.60s |
| #106 | GPT 5.3 Chat none | OpenAI | 1 | 6.7 | $0.533 | 2/4 | 3.86s |
| #129 | Kimi K2.6 medium | Moonshot AI | 1 | 7.0 | $1.247 | 2/4 | 11.6s |
| #145 | Mercury 2 medium | Inception | 1 | 6.9 | $0.094 | 2/4 | 1.12s |
| #169 | GLM 5V Turbo medium | Z.ai | 1 | 7.2 | $0.457 | 2/4 | 10.8s |
| #183 | Gemini 3.1 Flash Lite Preview none | 1 | 7.5 | $0.052 | 2/4 | 1.04s | |
| #199 | gpt-oss-120b medium | OpenAI | 1 | 6.7 | $0.070 | 2/4 | 10.2s |