Did not follow instructions Failures
See which AI models run into Did not follow instructions most often, so you can spot reliability risks before choosing one. Sort by: Total Cost ↓.
215/215
Filter models
No models match the current search and filters.
| Rank | Model | Company | Did not follow instructions Count | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #76 | Qwen3.6 Plus medium | Qwen | 1 | 7.8 | $0.418 | 15/22 | 45.5s |
| #157 | LongCat 2.0 low | Meituan | 1 | 6.7 | $0.412 | 10/22 | 113.6s |
| #114 | GLM 5.3 high | Z.ai | 1 | 7.3 | $0.403 | 13/22 | 27.8s |
| #55 | Inkling Small high | Thinkingmachines | 2 | 8.4 | $0.398 | 14/22 | 30.4s |
| #123 | Muse Glimmer 30B high | Meta | 3 | 7.2 | $0.397 | 10/22 | 66.7s |
| #214 | GPT-5.4 none | OpenAI | 1 | 5.8 | $0.397 | 7/22 | 2.08s |
| #181 | Mimo V2 PRO medium | Xiaomi | 1 | 6.3 | $0.333 | 12/21 | 22.2s |
| #289 | MiniMax M2.5 medium | Minimax | 3 | 4.6 | $0.327 | 5/22 | 69.1s |
| #90 | GLM 5 Turbo medium | Z.ai | 1 | 7.6 | $0.323 | 14/21 | 23.0s |
| #97 | MiniMax M3 medium | Minimax | 2 | 7.5 | $0.300 | 11/22 | 75.2s |
| #158 | Gemini 3.5 Flash minimal | 1 | 6.7 | $0.300 | 13/22 | 2.65s | |
| #53 | Qwen3.8 27B high | Qwen | 2 | 8.4 | ~$0.287 | 16/22 | 167.9s |
| #223 | Qwen3.5-122B-A10B none | Qwen | 2 | 5.7 | $0.283 | 6/22 | 12.9s |
| #202 | GPT-5.6 Terra none | OpenAI | 1 | 6.0 | $0.280 | 8/22 | 1.66s |
| #77 | Gemini 3.5 Flash Lite medium | 1 | 7.8 | $0.272 | 14/22 | 5.12s |