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) |
|---|---|---|---|---|---|---|---|
| #300 | Hy3 preview none | Tencent | 1 | 3.1 | $0.007 | 0/3 | 4.56s |
| #303 | Granite 4.1 8B none | IBM Granite | 1 | 3.2 | $0.007 | 0/3 | 608ms |
| #314 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 1 | 3.0 | $0.000 | 0/3 | 532ms |
| #62 | GPT-5 Mini medium | OpenAI | 1 | 5.6 | $0.241 | 1/3 | 15.2s |
| #64 | Inkling high | Thinkingmachines | 1 | 6.9 | $1.046 | 1/3 | 10.7s |
| #68 | GLM 5.2 high | Z.ai | 1 | 6.0 | $1.188 | 1/3 | 33.7s |
| #84 | Qwen3.7 Flash high | Qwen | 1 | 7.1 | $0.052 | 1/3 | 10.8s |
| #88 | DeepSeek V4 Pro high | DeepSeek | 1 | 6.9 | $0.476 | 1/3 | 56.8s |
| #107 | Kimi K2.7 Code medium | Moonshot AI | 1 | 5.9 | $0.687 | 1/3 | 41.0s |
| #121 | Kimi K2.6 medium | Moonshot AI | 1 | 6.0 | $1.247 | 1/3 | 25.1s |
| #123 | Muse Glimmer 30B high | Meta | 1 | 6.1 | $0.397 | 1/3 | 64.8s |
| #125 | Qwen3.7 Flash low | Qwen | 1 | 7.3 | $0.043 | 1/3 | 9.79s |
| #131 | Grok 4.3 medium | X AI | 1 | 5.9 | $0.741 | 1/3 | 22.5s |
| #133 | DeepSeek V3.2 medium | DeepSeek | 1 | 7.0 | $0.078 | 1/3 | 37.7s |
| #136 | Mercury 2 medium | Inception | 1 | 5.4 | $0.094 | 1/3 | 949ms |