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: Tests Correct ↑.
Failure Reasons
121/121
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) |
|---|---|---|---|---|---|---|---|
| #139 | Kimi K2.5 medium | Moonshot AI | 1 | 5.3 | $0.479 | 1/3 | 43.2s |
| #142 | Qwen3.7 Flash medium | Qwen | 1 | 7.1 | $0.065 | 1/3 | 8.30s |
| #152 | MiMo-V2.5-Pro medium | Xiaomi | 1 | 6.7 | $0.221 | 1/3 | 5.31s |
| #163 | Qwen3.5-27B none | Qwen | 1 | 6.7 | $0.058 | 1/3 | 1.38s |
| #165 | Inkling Small medium | Thinkingmachines | 1 | 5.8 | $0.113 | 1/3 | 5.24s |
| #175 | Dots 3 Note Preview low | Dots Studio | 1 | 5.3 | $0.000 | 1/3 | 8.52s |
| #180 | Ring-2.6-1T medium | Inclusionai | 1 | 5.9 | $0.102 | 1/3 | 20.7s |
| #181 | Mimo V2 PRO medium | Xiaomi | 1 | 6.4 | $0.333 | 1/3 | 5.08s |
| #187 | Gemini 3.1 Flash Lite minimal | 2 | 6.0 | $0.047 | 1/3 | 2.15s | |
| #189 | gpt-oss-120b medium | OpenAI | 1 | 5.3 | $0.020 | 1/3 | 21.7s |
| #191 | Gemini 3.1 Flash Lite none | 1 | 6.3 | $0.046 | 1/3 | 720ms | |
| #193 | Inkling low | Thinkingmachines | 1 | 6.4 | $0.187 | 1/3 | 2.97s |
| #196 | Gemma 4 31B none | 1 | 6.5 | $0.016 | 1/3 | 4.23s | |
| #198 | Nemotron 3 Ultra none | NVIDIA | 1 | 5.9 | $0.093 | 1/3 | 1.06s |
| #199 | Trinity Large Thinking low | Arcee AI | 1 | 6.3 | $0.625 | 1/3 | 3.28s |