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) |
|---|---|---|---|---|---|---|---|
| #258 | Solar Pro 4 high | Upstage | 3 | 0.6 | $0.077 | 11/23 | 128.9s |
| #221 | Qwen3.7 Flash medium | Qwen | 4 | 0.7 | $0.076 | 10/23 | 51.8s |
| #135 | GPT-6 Luna high | OpenAI | 1 | 0.8 | $0.074 | 15/23 | 20.4s |
| #170 | Qwen3.8 27B medium | Qwen | 2 | 0.7 | ~$0.073 | 14/23 | 40.1s |
| #140 | Qwen3.7 Flash low | Qwen | 3 | 0.8 | $0.071 | 12/23 | 41.0s |
| #372 | Qwen3 Coder Next medium | Qwen | 3 | 0.5 | $0.071 | 3/23 | 17.0s |
| #290 | Gemini 3.1 Flash Lite none | 1 | 0.6 | $0.069 | 9/23 | 3.58s | |
| #402 | Grok 4.1 Fast medium | X AI | 4 | 0.4 | $0.069 | 9/19 | 23.8s |
| #374 | GPT-5.4 Nano none | OpenAI | 2 | 0.5 | $0.068 | 4/23 | 4.42s |
| #207 | Solar Pro 4 xhigh | Upstage | 3 | 0.7 | $0.067 | 12/23 | 142.8s |
| #357 | Qwen3 Coder Next default | Qwen | 1 | 0.5 | $0.067 | 5/23 | 19.7s |
| #138 | Claude Haiku 5.5 medium | Anthropic | 2 | 0.8 | $0.063 | 13/23 | 7.71s |
| #173 | Qwen3.7 Flash high | Qwen | 1 | 0.7 | $0.063 | 13/23 | 45.5s |
| #75 | Claude Haiku 5.5 low | Anthropic | 2 | 0.9 | $0.061 | 16/23 | 7.51s |
| #327 | MiMo-V2.6-Flash none | Xiaomi | 1 | 0.5 | $0.060 | 6/23 | 6.20s |