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: Total Cost ↓.
Failure Reasons
157/157
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) |
|---|---|---|---|---|---|---|---|
| #330 | Hy3 preview medium | Tencent | 1 | 0.8 | $0.049 | 2/3 | 11.1s |
| #361 | MiMo-V2.5 none | Xiaomi | 1 | 0.5 | $0.049 | 1/3 | 2.13s |
| #95 | GPT-6 Luna medium | OpenAI | 1 | 0.8 | $0.047 | 2/3 | 9.78s |
| #344 | Mistral Small 4 none | Mistral | 1 | 0.3 | $0.047 | 0/3 | 399ms |
| #396 | GLM 5 Turbo none | Z.ai | 1 | 0.5 | $0.047 | 1/3 | 2.65s |
| #354 | KAT Coder AIR V2.5 low | Kwaipilot | 1 | 0.3 | $0.046 | 0/3 | 1.57s |
| #380 | Mimo V2 PRO default | Xiaomi | 1 | 0.6 | $0.045 | 1/3 | 1.61s |
| #114 | Qwen3.8 Flash Next low | Qwen | 1 | 0.9 | ~$0.045 | 2/3 | 1.72s |
| #362 | Qwen3.5-9B none | Qwen | 1 | 0.3 | $0.041 | 0/3 | 621ms |
| #314 | Nemotron 3.5 Super VL none | NVIDIA | 1 | 0.5 | $0.040 | 0/3 | 754ms |
| #218 | GLM 5.3 Flash low | Z.ai | 1 | 0.8 | $0.038 | 2/3 | 2.67s |
| #144 | GPT-6 Luna low | OpenAI | 1 | 0.8 | $0.033 | 2/3 | 27.5s |
| #307 | Gemma 4 31B none | 1 | 0.6 | $0.031 | 1/3 | 4.23s | |
| #320 | Gemma 4 26B A4B none | 1 | 0.6 | $0.031 | 1/3 | 744ms | |
| #289 | gpt-oss-120b medium | OpenAI | 1 | 0.5 | $0.030 | 1/3 | 21.7s |