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: Total Cost ↑.
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) |
|---|---|---|---|---|---|---|---|
| #325 | gpt-oss-120b none | OpenAI | 1 | 6.5 | $0.033 | 2/4 | 32.8s |
| #300 | Qwen3 Coder Next medium | Qwen | 1 | 3.5 | $0.034 | 0/4 | 8.64s |
| #308 | Granite 4.2 8B none | IBM Granite | 1 | 4.9 | $0.037 | 1/4 | 17.8s |
| #183 | Gemini 3.1 Flash Lite Preview none | 1 | 7.5 | $0.052 | 2/4 | 1.04s | |
| #229 | Inkling Small low | Thinkingmachines | 1 | 9.2 | $0.055 | 3/4 | 1.81s |
| #253 | MiMo-V2.5-Pro none | Xiaomi | 1 | 3.3 | $0.068 | 0/4 | 2.67s |
| #199 | gpt-oss-120b medium | OpenAI | 1 | 6.7 | $0.070 | 2/4 | 10.2s |
| #145 | Mercury 2 medium | Inception | 1 | 6.9 | $0.094 | 2/4 | 1.12s |
| #113 | Gemini 3.1 Flash Lite Preview medium | 1 | 9.1 | $0.117 | 3/4 | 2.33s | |
| #125 | Gemini 3.1 Flash Lite medium | 1 | 9.1 | $0.120 | 3/4 | 2.39s | |
| #172 | Gemini 3.5 Flash Lite low | 1 | 9.0 | $0.138 | 3/4 | 1.69s | |
| #259 | Seed-2.0-Code none | Bytedance Seed | 1 | 3.0 | $0.151 | 0/4 | 5.06s |
| #306 | GLM 4.7 Flash medium | Z.ai | 1 | 4.7 | $0.168 | 1/4 | 15.0s |
| #276 | MiniMax M2.7 medium | Minimax | 1 | 7.9 | $0.208 | 2/4 | 40.3s |
| #70 | GPT-5 Mini medium | OpenAI | 1 | 7.1 | $0.241 | 2/4 | 13.9s |