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: Failure Count ↑.
145/145
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) |
|---|---|---|---|---|---|---|---|
| #155 | KAT-Coder-Air V2.5 medium | Kwaipilot | 1 | 5.6 | $0.048 | 8/22 | 8.42s |
| #156 | DeepSeek V4 Flash none | DeepSeek | 1 | 5.6 | $0.044 | 5/22 | 36.8s |
| #163 | Mimo V2 Omni none | Xiaomi | 1 | 5.5 | $0.021 | 8/21 | 2.44s |
| #164 | Laguna S 2.1 medium | Poolside | 1 | 5.4 | $0.059 | 4/22 | 58.4s |
| #167 | Laguna S 2.1 high | Poolside | 1 | 5.4 | $0.127 | 4/22 | 111.6s |
| #168 | Laguna XS 2.1 none | Poolside | 1 | 5.3 | $0.008 | 5/22 | 1.55s |
| #171 | Gemini 3.1 Flash Lite Preview high | 1 | 5.3 | $2.310 | 13/16 | 68.1s | |
| #172 | Inkling none | Thinkingmachines | 1 | 5.2 | $0.147 | 6/22 | 3.50s |
| #173 | Mistral Small 4 none | Mistral | 1 | 5.1 | $0.022 | 5/22 | 1.20s |
| #174 | Qwen3 Coder Next none | Qwen | 1 | 5.1 | $0.025 | 5/22 | 9.12s |
| #176 | MiMo-V2.5 none | Xiaomi | 1 | 5.1 | $0.025 | 5/22 | 4.62s |
| #181 | Laguna S 2.1 low | Poolside | 1 | 5.0 | $0.091 | 3/22 | 85.3s |
| #182 | DeepSeek V3.2 none | DeepSeek | 1 | 5.0 | $0.054 | 6/22 | 18.3s |
| #183 | GPT-4o-mini none | OpenAI | 1 | 5.0 | $0.010 | 5/22 | 1.99s |
| #185 | GLM 4.7 Flash none | Z.ai | 1 | 4.9 | $0.016 | 6/22 | 9.15s |