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
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) |
|---|---|---|---|---|---|---|---|
| #297 | GPT-5.6 Terra none | OpenAI | 1 | 0.9 | $0.377 | 1/2 | 1.15s |
| #306 | Dots 3 Note Preview medium | Dots Studio | 1 | 0.8 | $0.000 | 1/2 | 7.77s |
| #308 | Space Bunny Alpha low | Stealth | 1 | 0.4 | $0.000 | 0/2 | 1.43s |
| #315 | Nemotron 3 Super medium | NVIDIA | 1 | 0.7 | $0.081 | 1/2 | 6.97s |
| #317 | Ling 3.1 Flash none | Inclusionai | 1 | 0.8 | $0.000 | 1/2 | 1.22s |
| #328 | Step 3.5 Flash medium | Stepfun | 1 | 0.8 | $0.105 | 1/2 | 4.78s |
| #338 | Ling 3.0 Flash none | Inclusionai | 1 | 0.5 | $0.004 | 0/2 | 836ms |
| #339 | Nemotron 3.5 Lightning high | NVIDIA | 1 | 0.8 | $0.168 | 1/2 | 4.98s |
| #348 | Apodex 1.1 Mini default | Apodex | 1 | 0.5 | $0.000 | 0/2 | 1.06s |
| #349 | Laguna S 2.1 medium | Poolside | 1 | 0.4 | $0.092 | 0/2 | 400ms |
| #351 | MiniMax M2.7 medium | Minimax | 1 | 0.4 | $0.326 | 0/2 | 12.8s |
| #352 | Dots 3 Note Preview default | Dots Studio | 1 | 0.5 | $0.000 | 0/2 | 1.06s |
| #358 | Laguna S 2.1 high | Poolside | 1 | 0.5 | $0.145 | 0/2 | 453ms |
| #364 | Mimo V2 Omni medium | Xiaomi | 1 | 0.8 | $0.683 | 1/2 | 4.99s |
| #368 | Nemotron 3.5 Lightning medium | NVIDIA | 1 | 0.9 | $0.195 | 1/2 | 3.75s |