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
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) |
|---|---|---|---|---|---|---|---|
| #84 | GPT-5 Mini medium | OpenAI | 1 | 0.6 | $0.315 | 1/3 | 15.2s |
| #87 | Inkling high | Thinkingmachines | 1 | 0.7 | $1.238 | 1/3 | 10.7s |
| #90 | GLM 5.2 high | Z.ai | 1 | 0.6 | $4.632 | 1/3 | 33.7s |
| #92 | Claude Haiku 5.5 high | Anthropic | 1 | 0.6 | $0.088 | 1/3 | 3.28s |
| #100 | DeepSeek V4.1 Flash 1017 max | DeepSeek | 1 | 0.6 | $0.757 | 1/3 | 12.3s |
| #106 | DeepSeek V4 Pro 0423 high | DeepSeek | 1 | 0.7 | $0.149 | 1/3 | 56.8s |
| #126 | DeepSeek V4.1 Flash 1017 high | DeepSeek | 1 | 0.5 | $0.589 | 1/3 | 5.70s |
| #136 | Muse Glimmer 30B high | Meta | 1 | 0.6 | $0.506 | 1/3 | 64.8s |
| #140 | Qwen3.7 Flash low | Qwen | 1 | 0.7 | $0.071 | 1/3 | 9.79s |
| #168 | Qwen3.5-27B none | Qwen | 1 | 0.7 | $0.116 | 1/3 | 1.38s |
| #173 | Qwen3.7 Flash high | Qwen | 1 | 0.7 | $0.063 | 1/3 | 10.8s |
| #187 | Kimi K2.7 Code medium | Moonshot AI | 1 | 0.6 | $1.136 | 1/3 | 41.0s |
| #201 | Kimi K2.6 medium | Moonshot AI | 1 | 0.6 | $1.594 | 1/3 | 25.1s |
| #203 | Inkling low | Thinkingmachines | 1 | 0.6 | $0.293 | 1/3 | 2.97s |
| #221 | Qwen3.7 Flash medium | Qwen | 1 | 0.7 | $0.076 | 1/3 | 8.30s |