Instructions following: Did not follow instructions
Instructions following
Did not follow instructions
See which AI models are most likely to hit Did not follow instructions on Instructions following, so you can spot weak points faster. Sort by: Tests Correct ↑.
Failure Reasons
77/77
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) |
|---|---|---|---|---|---|---|---|
| #163 | Grok 4.7 medium | X AI | 1 | 0.8 | $2.938 | 1/2 | 6.68s |
| #182 | MiMo-V2.6-Flash low | Xiaomi | 1 | 0.8 | $0.200 | 1/2 | 955ms |
| #193 | Muse Glimmer 30B low | Meta | 1 | 0.8 | $0.219 | 1/2 | 3.60s |
| #198 | GPT-5.6 Luna low | OpenAI | 1 | 0.8 | $0.049 | 1/2 | 2.04s |
| #199 | Claude Sonnet 5.5 low | Anthropic | 1 | 0.6 | $0.909 | 1/2 | 1.91s |
| #207 | Solar Pro 4 xhigh | Upstage | 1 | 0.8 | $0.067 | 1/2 | 51.3s |
| #211 | Solar Pro 4 low | Upstage | 1 | 0.8 | $0.101 | 1/2 | 56.4s |
| #212 | Grok 4.7 high | X AI | 1 | 0.8 | $3.037 | 1/2 | 14.1s |
| #216 | GPT-5.6 Sol none | OpenAI | 1 | 0.9 | $0.795 | 1/2 | 1.33s |
| #217 | Apodex 1.1 Mini high | Apodex | 1 | 0.8 | $0.000 | 1/2 | 8.10s |
| #240 | Beam 1.0 501B A23B max | Reflection | 1 | 0.8 | $0.799 | 1/2 | 866ms |
| #245 | Beam 1.0 501B A23B low | Reflection | 1 | 0.8 | $0.432 | 1/2 | 1.14s |
| #249 | Dots 3 Note Preview high | Dots Studio | 1 | 0.8 | $0.000 | 1/2 | 7.80s |
| #250 | Dots 3 Note Preview low | Dots Studio | 1 | 0.8 | $0.000 | 1/2 | 7.83s |
| #258 | Solar Pro 4 high | Upstage | 1 | 0.8 | $0.077 | 1/2 | 41.5s |