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
32/32
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) |
|---|---|---|---|---|---|---|---|
| #82 | DeepSeek V4 Pro none | DeepSeek | 1 | 3.2 | $0.096 | 0/4 | 4.02s |
| #148 | Owl Alpha none | Openrouter | 1 | 3.4 | $0.000 | 0/4 | 2.78s |
| #154 | MiMo-V2.5-Pro none | Xiaomi | 1 | 3.3 | $0.068 | 0/4 | 2.67s |
| #157 | Mimo V2 Omni none | Xiaomi | 1 | 3.6 | $0.021 | 0/4 | 1.63s |
| #166 | Qwen3 Coder Next none | Qwen | 1 | 3.6 | $0.025 | 0/4 | 3.31s |
| #187 | Qwen3 Coder Next medium | Qwen | 1 | 3.5 | $0.032 | 0/4 | 8.64s |
| #203 | Grok 4.1 Fast none | X AI | 1 | 3.2 | $0.008 | 0/4 | 1.07s |
| #205 | Laguna Xs.2 none | Poolside | 1 | 3.0 | $0.004 | 0/4 | 534ms |
| #47 | MiniMax M3 medium | Minimax | 1 | 5.5 | $0.286 | 1/4 | 14.9s |
| #160 | Laguna XS 2.1 none | Poolside | 1 | 5.3 | $0.008 | 1/4 | 755ms |
| #194 | GLM 4.7 Flash medium | Z.ai | 1 | 4.7 | $0.166 | 1/4 | 15.0s |
| #199 | Hy3 preview none | Tencent | 2 | 4.8 | $0.003 | 1/4 | 11.1s |
| #201 | Granite 4.1 8B none | IBM Granite | 1 | 4.9 | $0.007 | 1/4 | 844ms |
| #21 | GPT-5.2 medium | OpenAI | 1 | 6.5 | $0.951 | 2/4 | 7.81s |
| #26 | GPT-5 Mini medium | OpenAI | 1 | 7.1 | $0.237 | 2/4 | 13.9s |