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
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) |
|---|---|---|---|---|---|---|---|
| #174 | GPT-4o-mini none | OpenAI | 1 | 3.5 | $0.010 | 0/3 | 1.21s |
| #156 | Gemma 4 26B A4B none | 1 | 6.2 | $0.015 | 1/3 | 744ms | |
| #162 | Ling-2.6-1T none | Inclusionai | 1 | 3.1 | $0.016 | 0/3 | 5.36s |
| #176 | GLM 4.7 Flash none | Z.ai | 1 | 6.4 | $0.016 | 1/3 | 1.20s |
| #100 | Hy3 preview medium | Tencent | 1 | 7.7 | $0.018 | 2/3 | 11.1s |
| #121 | gpt-oss-120b medium | OpenAI | 1 | 5.3 | $0.019 | 1/3 | 21.7s |
| #169 | Qwen3.5-9B none | Qwen | 1 | 3.2 | $0.021 | 0/3 | 621ms |
| #165 | Mistral Small 4 none | Mistral | 1 | 3.1 | $0.022 | 0/3 | 399ms |
| #168 | MiMo-V2.5 none | Xiaomi | 1 | 5.4 | $0.025 | 1/3 | 2.13s |
| #179 | Ring-2.6-1T none | Inclusionai | 1 | 7.7 | $0.026 | 2/3 | 31.5s |
| #187 | Qwen3 Coder Next medium | Qwen | 1 | 3.0 | $0.032 | 0/3 | 1.25s |
| #115 | Gemma 4 31B none | 1 | 6.5 | $0.035 | 1/3 | 4.23s | |
| #180 | GPT-5.4 Nano none | OpenAI | 1 | 5.4 | $0.041 | 1/3 | 1.25s |
| #158 | KAT-Coder-Air V2.5 low | Kwaipilot | 1 | 3.1 | $0.041 | 0/3 | 1.57s |
| #45 | DeepSeek V4 Flash high | DeepSeek | 1 | 8.2 | $0.042 | 2/3 | 26.1s |