Puzzle Solving: Did not follow instructions
Puzzle Solving
Did not follow instructions
See which AI models are most likely to hit Did not follow instructions on Puzzle Solving, so you can spot weak points faster. Sort by: Response Time (avg) ↓.
Failure Reasons
86/86
Filter models
No models match the current search and filters.
| Rank | Model | Company | Did not follow instructions Count | Category Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #189 | Trinity Large Preview none | Arcee AI | 1 | 3.6 | $0.008 | 0/3 | 1.97s |
| #153 | Mimo V2 PRO none | Xiaomi | 1 | 6.0 | $0.045 | 1/3 | 1.61s |
| #164 | KAT-Coder-Air V2.5 low | Kwaipilot | 1 | 3.1 | $0.041 | 0/3 | 1.57s |
| #145 | GPT-5.4 none | OpenAI | 1 | 5.6 | $0.397 | 1/3 | 1.44s |
| #144 | Kimi K2.6 none | Moonshot AI | 1 | 3.1 | $0.184 | 0/3 | 1.40s |
| #109 | Qwen3.5-27B none | Qwen | 1 | 6.7 | $0.090 | 1/3 | 1.38s |
| #133 | Qwen3.5-35B-A3B none | Qwen | 1 | 3.7 | $0.106 | 0/3 | 1.35s |
| #160 | MiMo-V2.5-Pro none | Xiaomi | 1 | 6.7 | $0.068 | 1/3 | 1.30s |
| #186 | GPT-5.4 Nano none | OpenAI | 1 | 5.4 | $0.041 | 1/3 | 1.25s |
| #193 | Qwen3 Coder Next medium | Qwen | 1 | 3.0 | $0.032 | 0/3 | 1.25s |
| #130 | Qwen3.6 Flash none | Qwen | 1 | 3.5 | $0.062 | 0/3 | 1.21s |
| #180 | GPT-4o-mini none | OpenAI | 1 | 3.5 | $0.010 | 0/3 | 1.21s |
| #182 | GLM 4.7 Flash none | Z.ai | 1 | 6.4 | $0.016 | 1/3 | 1.20s |
| #167 | Qwen3.6 35B A3B none | Qwen | 2 | 3.2 | $0.061 | 0/3 | 1.07s |
| #135 | Nemotron 3 Ultra none | NVIDIA | 1 | 5.9 | $0.095 | 1/3 | 1.06s |