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 ↓.
Categories
293/293
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) |
|---|---|---|---|---|---|---|---|
| #161 | GLM 5.3 Flash high | Z.ai | 2 | 0.7 | $0.056 | 13/23 | 29.1s |
| #337 | Inkling Small low | Thinkingmachines | 2 | 0.5 | $0.055 | 9/23 | 1.99s |
| #296 | DeepSeek V4.1 Flash 1017 none | DeepSeek | 1 | 0.6 | $0.055 | 8/23 | 3.46s |
| #356 | Inkling Small none | Thinkingmachines | 1 | 0.5 | $0.054 | 5/23 | 1.45s |
| #270 | DeepSeek V4 Flash 0731 none | DeepSeek | 2 | 0.6 | $0.053 | 5/23 | 27.4s |
| #376 | GLM 5V Turbo none | Z.ai | 2 | 0.5 | $0.052 | 8/21 | 2.99s |
| #330 | Hy3 preview medium | Tencent | 1 | 0.5 | $0.049 | 14/21 | 16.3s |
| #198 | GPT-5.6 Luna low | OpenAI | 1 | 0.7 | $0.049 | 11/23 | 6.96s |
| #361 | MiMo-V2.5 none | Xiaomi | 1 | 0.5 | $0.049 | 5/23 | 9.88s |
| #346 | KAT Coder AIR V2.5 medium | Kwaipilot | 1 | 0.5 | $0.048 | 8/23 | 8.32s |
| #143 | Qwen3.8 Flash Next medium | Qwen | 1 | 0.8 | ~$0.047 | 15/23 | 24.8s |
| #95 | GPT-6 Luna medium | OpenAI | 1 | 0.8 | $0.047 | 15/23 | 18.1s |
| #344 | Mistral Small 4 none | Mistral | 1 | 0.5 | $0.047 | 5/23 | 3.12s |
| #396 | GLM 5 Turbo none | Z.ai | 2 | 0.4 | $0.047 | 6/21 | 2.82s |
| #354 | KAT Coder AIR V2.5 low | Kwaipilot | 2 | 0.5 | $0.046 | 7/23 | 10.2s |