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: Response Time (avg) ↓.
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) |
|---|---|---|---|---|---|---|---|
| #404 | Ling 3.0 Tiny default | Inclusionai | 1 | 0.3 | $0.000 | 0/2 | 2.44s |
| #267 | Space Bunny Alpha xhigh | Stealth | 1 | 0.6 | $0.000 | 0/2 | 2.22s |
| #198 | GPT-5.6 Luna low | OpenAI | 1 | 0.8 | $0.049 | 1/2 | 2.04s |
| #135 | GPT-6 Luna high | OpenAI | 1 | 0.8 | $0.074 | 1/2 | 1.92s |
| #199 | Claude Sonnet 5.5 low | Anthropic | 1 | 0.6 | $0.909 | 1/2 | 1.91s |
| #68 | MiMo-V2.6-Pro medium | Xiaomi | 1 | 0.8 | $0.586 | 1/2 | 1.79s |
| #194 | Minimax M3.1 Flash max | Minimax | 1 | 0.5 | $0.000 | 0/2 | 1.73s |
| #243 | Minimax M3.1 Flash xhigh | Minimax | 1 | 0.5 | $0.000 | 0/2 | 1.72s |
| #256 | Minimax M3.1 Flash medium | Minimax | 1 | 0.5 | $0.000 | 0/2 | 1.72s |
| #228 | Minimax M3.1 Flash high | Minimax | 1 | 0.5 | $0.000 | 0/2 | 1.65s |
| #308 | Space Bunny Alpha low | Stealth | 1 | 0.4 | $0.000 | 0/2 | 1.43s |
| #270 | DeepSeek V4 Flash 0731 none | DeepSeek | 1 | 0.5 | $0.053 | 0/2 | 1.42s |
| #429 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 1 | 0.7 | $0.000 | 1/2 | 1.37s |
| #216 | GPT-5.6 Sol none | OpenAI | 1 | 0.9 | $0.795 | 1/2 | 1.33s |
| #317 | Ling 3.1 Flash none | Inclusionai | 1 | 0.8 | $0.000 | 1/2 | 1.22s |