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.
Failure Reasons
18/18
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) |
|---|---|---|---|---|---|---|---|
| #16 | Muse Spark 1.1 medium | Meta | 1 | 6.5 | $1.357 | 1/2 | 6.31s |
| #24 | Muse Spark 1.1 low | Meta | 1 | 7.3 | $0.647 | 1/2 | 5.42s |
| #27 | Muse Spark 1.1 high | Meta | 1 | 6.4 | $1.694 | 1/2 | 7.81s |
| #46 | DeepSeek V4 Pro high | DeepSeek | 1 | 7.8 | $0.200 | 1/2 | 8.73s |
| #83 | GPT-5.6 Sol none | OpenAI | 1 | 8.5 | $0.524 | 1/2 | 1.33s |
| #117 | GPT-5.6 Luna low | OpenAI | 1 | 8.5 | $0.249 | 1/2 | 2.04s |
| #130 | Step 3.5 Flash medium | Stepfun | 1 | 8.3 | $0.108 | 1/2 | 4.78s |
| #132 | GPT-5.6 Terra none | OpenAI | 1 | 8.5 | $0.349 | 1/2 | 1.15s |
| #134 | Mimo V2 Omni medium | Xiaomi | 1 | 8.3 | $0.683 | 1/2 | 4.99s |
| #140 | Nemotron 3 Super medium | NVIDIA | 1 | 7.3 | $0.050 | 1/2 | 6.97s |
| #172 | MiniMax M2.7 medium | Minimax | 1 | 3.8 | $0.163 | 0/2 | 12.8s |
| #183 | Trinity Large Preview none | Arcee AI | 1 | 3.5 | $0.008 | 0/2 | 822ms |
| #185 | Grok 4.1 Fast medium | X AI | 1 | 6.5 | $0.069 | 1/2 | 4.63s |
| #190 | MiniMax M2.5 medium | Minimax | 1 | 7.5 | $0.340 | 1/2 | 621ms |
| #201 | Granite 4.1 8B none | IBM Granite | 1 | 3.6 | $0.007 | 0/2 | 344ms |