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: Score ↑.
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) |
|---|---|---|---|---|---|---|---|
| #250 | Gemini 3.1 Flash Lite Preview high | 1 | 5.3 | $2.310 | 13/16 | 68.1s | |
| #249 | Ling-2.6-1T none | Inclusionai | 2 | 5.3 | $0.016 | 4/22 | 8.59s |
| #248 | Seed-2.0-Code none | Bytedance Seed | 2 | 5.3 | $0.151 | 6/22 | 14.7s |
| #247 | Laguna XS 2.1 none | Poolside | 1 | 5.3 | $0.008 | 5/22 | 1.55s |
| #246 | Inkling Small none | Thinkingmachines | 1 | 5.3 | $0.054 | 5/22 | 1.51s |
| #244 | DeepSeek V4 Flash 0731 none | DeepSeek | 2 | 5.4 | $0.011 | 4/22 | 20.7s |
| #245 | Laguna S 2.1 high | Poolside | 1 | 5.4 | $0.114 | 4/22 | 111.6s |
| #242 | MiMo-V2.5-Pro none | Xiaomi | 4 | 5.4 | $0.068 | 5/22 | 4.24s |
| #240 | KAT-Coder-Air V2.5 low | Kwaipilot | 2 | 5.4 | $0.046 | 7/22 | 10.6s |
| #239 | Laguna S 2.1 medium | Poolside | 1 | 5.4 | $0.053 | 4/22 | 58.4s |
| #238 | DeepSeek V4 Flash 0423 none | DeepSeek | 1 | 5.4 | $0.039 | 4/22 | 36.2s |
| #237 | Mimo V2 Omni none | Xiaomi | 1 | 5.5 | $0.021 | 8/21 | 2.44s |
| #236 | Qwen3.8 27B none | Qwen | 1 | 5.5 | ~$0.006 | 9/22 | 3.12s |
| #234 | Qwen3.6 27B none | Qwen | 2 | 5.5 | $0.062 | 7/22 | 10.6s |
| #233 | Hy4 preview low | Tencent | 1 | 5.6 | $1.745 | 3/22 | 214.3s |