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) |
|---|---|---|---|---|---|---|---|
| #187 | Kimi K2.7 Code medium | Moonshot AI | 1 | 0.6 | $1.136 | 1/3 | 41.0s |
| #71 | DeepSeek V4.1 Flash max | DeepSeek | 1 | 0.6 | $1.204 | 1/3 | 30.8s |
| #87 | Inkling high | Thinkingmachines | 1 | 0.7 | $1.238 | 1/3 | 10.7s |
| #62 | Muse Spark Open medium | Meta | 1 | 0.8 | $1.260 | 2/3 | 29.4s |
| #38 | GPT-5.3-Codex medium | OpenAI | 1 | 0.9 | $1.318 | 2/3 | 5.05s |
| #66 | GPT-5.2 medium | OpenAI | 1 | 0.7 | $1.558 | 2/3 | 5.80s |
| #56 | Muse Spark 1.2 medium | Meta | 1 | 0.9 | $1.590 | 2/3 | 9.45s |
| #201 | Kimi K2.6 medium | Moonshot AI | 1 | 0.6 | $1.594 | 1/3 | 25.1s |
| #57 | Muse Spark 1.1 medium | Meta | 1 | 0.8 | $1.665 | 2/3 | 42.5s |
| #24 | Claude Opus 5.5 low | Anthropic | 1 | 0.9 | $1.733 | 2/3 | 29.8s |
| #30 | Muse Spark Open high | Meta | 1 | 0.8 | $1.782 | 2/3 | 145.7s |
| #326 | Hy4 preview low | Tencent | 1 | 0.5 | $1.844 | 0/3 | 238.0s |
| #40 | Muse Spark 1.3 high | Meta | 1 | 0.9 | $1.891 | 2/3 | 38.4s |
| #55 | Muse Spark 1.2 high | Meta | 1 | 0.8 | $2.018 | 2/3 | 10.1s |
| #375 | Gemini 3.1 Flash Lite high | 2 | 0.6 | $2.044 | 1/3 | 50.8s |