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) |
|---|---|---|---|---|---|---|---|
| #402 | Grok 4.1 Fast medium | X AI | 1 | 0.7 | $0.069 | 1/2 | 4.63s |
| #408 | Ling 3.0 Tiny high | Inclusionai | 1 | 0.7 | $0.000 | 1/2 | 3.10s |
| #409 | Ling 3.0 Tiny low | Inclusionai | 1 | 0.7 | $0.000 | 1/2 | 3.09s |
| #410 | Ling 3.0 Tiny medium | Inclusionai | 1 | 0.7 | $0.000 | 1/2 | 3.00s |
| #429 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 1 | 0.7 | $0.000 | 1/2 | 1.37s |
| #194 | Minimax M3.1 Flash max | Minimax | 1 | 0.5 | $0.000 | 0/2 | 1.73s |
| #206 | Space Bunny Alpha max | Stealth | 1 | 0.6 | $0.000 | 0/2 | 3.78s |
| #221 | Qwen3.7 Flash medium | Qwen | 1 | 0.6 | $0.076 | 0/2 | 9.27s |
| #228 | Minimax M3.1 Flash high | Minimax | 1 | 0.5 | $0.000 | 0/2 | 1.65s |
| #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 |
| #264 | Trinity Large Thinking low | Arcee AI | 1 | 0.4 | $0.918 | 0/2 | 4.07s |
| #267 | Space Bunny Alpha xhigh | Stealth | 1 | 0.6 | $0.000 | 0/2 | 2.22s |
| #270 | DeepSeek V4 Flash 0731 none | DeepSeek | 1 | 0.5 | $0.053 | 0/2 | 1.42s |
| #275 | Trinity Large Thinking medium | Arcee AI | 1 | 0.4 | $0.862 | 0/2 | 3.99s |