General Intelligence: Did not follow instructions
General Intelligence
Did not follow instructions
See which AI models are most likely to hit Did not follow instructions on General Intelligence, so you can spot weak points faster. Sort by: Tests Correct ↓.
Failure Reasons
78/78
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) |
|---|---|---|---|---|---|---|---|
| #142 | Qwen3.5-122B-A10B none | Qwen | 1 | 5.0 | $0.247 | 0/1 | 1.12s |
| #143 | Gemini 3.1 Flash Lite high | 1 | 5.0 | $2.044 | 0/1 | 45.7s | |
| #145 | GLM 5V Turbo none | Z.ai | 1 | 4.6 | $0.052 | 0/1 | 2.22s |
| #146 | Owl Alpha medium | Openrouter | 1 | 4.3 | $0.000 | 0/1 | 58.6s |
| #147 | Mimo V2 PRO none | Xiaomi | 1 | 4.3 | $0.045 | 0/1 | 2.44s |
| #148 | Owl Alpha none | Openrouter | 1 | 4.3 | $0.000 | 0/1 | 4.61s |
| #149 | KAT-Coder-Air V2.5 medium | Kwaipilot | 1 | 5.0 | $0.048 | 0/1 | 9.81s |
| #152 | Qwen3.6 27B none | Qwen | 1 | 5.2 | $0.087 | 0/1 | 1.07s |
| #156 | Gemma 4 26B A4B none | 1 | 4.0 | $0.015 | 0/1 | 3.54s | |
| #158 | KAT-Coder-Air V2.5 low | Kwaipilot | 1 | 5.0 | $0.041 | 0/1 | 10.1s |
| #162 | Ling-2.6-1T none | Inclusionai | 1 | 5.0 | $0.016 | 0/1 | 20.3s |
| #167 | Mistral Small 4 medium | Mistral | 1 | 4.8 | $0.096 | 0/1 | 2.05s |
| #169 | Qwen3.5-9B none | Qwen | 1 | 4.4 | $0.021 | 0/1 | 552ms |
| #170 | GLM 5 Turbo none | Z.ai | 1 | 4.2 | $0.047 | 0/1 | 2.18s |
| #172 | MiniMax M2.7 medium | Minimax | 1 | 3.9 | $0.163 | 0/1 | 38.7s |