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) |
|---|---|---|---|---|---|---|---|
| #185 | Ring-2.6-1T none | Inclusionai | 1 | 7.7 | $0.026 | 2/3 | 31.5s |
| #174 | MiMo-V2.5 none | Xiaomi | 1 | 5.4 | $0.025 | 1/3 | 2.13s |
| #171 | Mistral Small 4 none | Mistral | 1 | 3.1 | $0.022 | 0/3 | 399ms |
| #175 | Qwen3.5-9B none | Qwen | 1 | 3.2 | $0.021 | 0/3 | 621ms |
| #121 | Gemma 4 31B none | 1 | 6.5 | $0.021 | 1/3 | 4.23s | |
| #127 | gpt-oss-120b medium | OpenAI | 1 | 5.3 | $0.019 | 1/3 | 21.7s |
| #106 | Hy3 preview medium | Tencent | 1 | 7.7 | $0.018 | 2/3 | 11.1s |
| #182 | GLM 4.7 Flash none | Z.ai | 1 | 6.4 | $0.016 | 1/3 | 1.20s |
| #168 | Ling-2.6-1T none | Inclusionai | 1 | 3.1 | $0.016 | 0/3 | 5.36s |
| #162 | Gemma 4 26B A4B none | 1 | 6.2 | $0.015 | 1/3 | 744ms | |
| #180 | GPT-4o-mini none | OpenAI | 1 | 3.5 | $0.010 | 0/3 | 1.21s |
| #212 | gpt-oss-120b none | OpenAI | 1 | 6.0 | $0.010 | 1/3 | 8.21s |
| #183 | Nemotron 3 Super none | NVIDIA | 1 | 5.5 | $0.008 | 1/3 | 2.36s |
| #189 | Trinity Large Preview none | Arcee AI | 1 | 3.6 | $0.008 | 0/3 | 1.97s |
| #207 | Granite 4.1 8B none | IBM Granite | 1 | 3.2 | $0.007 | 0/3 | 608ms |