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: Total Cost ↓.
Failure Reasons
122/122
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) |
|---|---|---|---|---|---|---|---|
| #170 | MiMo-V2.5-Pro medium | Xiaomi | 1 | 5.5 | $0.221 | 0/1 | 4.02s |
| #289 | MiniMax M2.7 medium | Minimax | 1 | 3.9 | $0.208 | 0/1 | 38.7s |
| #262 | DeepSeek V4.1 Flash none | DeepSeek | 1 | 5.5 | $0.185 | 0/1 | 1.69s |
| #102 | MiMo-V2.6-Flash low | Xiaomi | 1 | 4.8 | $0.174 | 0/1 | 1.60s |
| #169 | GLM 5.3 low | Z.ai | 1 | 4.1 | $0.167 | 0/1 | 4.70s |
| #279 | Nemotron 3.5 Lightning medium | NVIDIA | 1 | 5.5 | $0.155 | 0/1 | 4.36s |
| #144 | Muse Glimmer 30B low | Meta | 1 | 5.0 | $0.152 | 0/1 | 2.50s |
| #228 | Qwen3.5-35B-A3B none | Qwen | 1 | 6.5 | $0.151 | 0/1 | 1.19s |
| #105 | Solar Pro 4 xhigh | Upstage | 1 | 5.5 | $0.150 | 0/1 | 61.9s |
| #109 | GPT-5.4 Nano medium | OpenAI | 1 | 4.5 | $0.142 | 0/1 | 4.15s |
| #214 | Qwen3.5-Flash medium | Qwen | 1 | 6.1 | $0.142 | 0/1 | 40.1s |
| #167 | Solar Pro 4 medium | Upstage | 1 | 3.0 | $0.140 | 0/1 | 48.0s |
| #146 | Solar Pro 4 high | Upstage | 1 | 5.5 | $0.138 | 0/1 | 42.2s |
| #165 | GLM 5.3 FlashX high | Z.ai | 1 | 6.1 | $0.135 | 0/1 | 2.28s |
| #229 | Step 3.5 Flash medium | Stepfun | 1 | 5.5 | $0.132 | 0/1 | 22.4s |