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: Total Cost ↑.
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) |
|---|---|---|---|---|---|---|---|
| #216 | GPT-5.6 Sol none | OpenAI | 1 | 0.9 | $0.795 | 1/2 | 1.33s |
| #240 | Beam 1.0 501B A23B max | Reflection | 1 | 0.8 | $0.799 | 1/2 | 866ms |
| #275 | Trinity Large Thinking medium | Arcee AI | 1 | 0.4 | $0.862 | 0/2 | 3.99s |
| #72 | Muse Spark 1.1 low | Meta | 1 | 0.7 | $0.885 | 1/2 | 5.42s |
| #199 | Claude Sonnet 5.5 low | Anthropic | 1 | 0.6 | $0.909 | 1/2 | 1.91s |
| #264 | Trinity Large Thinking low | Arcee AI | 1 | 0.4 | $0.918 | 0/2 | 4.07s |
| #62 | Muse Spark Open medium | Meta | 1 | 0.7 | $1.260 | 1/2 | 18.4s |
| #149 | Mistral Large 4 high | Mistral | 1 | 0.8 | $1.391 | 1/2 | 22.0s |
| #57 | Muse Spark 1.1 medium | Meta | 1 | 0.7 | $1.665 | 1/2 | 6.31s |
| #40 | Muse Spark 1.3 high | Meta | 1 | 0.7 | $1.891 | 1/2 | 14.7s |
| #156 | Grok 4.7 low | X AI | 1 | 0.8 | $1.933 | 1/2 | 6.19s |
| #88 | Muse Spark 1.1 high | Meta | 1 | 0.6 | $2.570 | 1/2 | 7.81s |
| #163 | Grok 4.7 medium | X AI | 1 | 0.8 | $2.938 | 1/2 | 6.68s |
| #212 | Grok 4.7 high | X AI | 1 | 0.8 | $3.037 | 1/2 | 14.1s |
| #162 | Claude Fable 5.1 medium | Anthropic | 1 | 0.7 | $3.197 | 1/2 | 5.77s |