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
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 |
| #88 | DeepSeek V4 Pro high | DeepSeek | 1 | 6.9 | $0.476 | 1/3 | 56.8s |
| #157 | LongCat 2.0 low | Meituan | 1 | 3.1 | $0.412 | 0/3 | 8.15s |
| #55 | Inkling Small high | Thinkingmachines | 1 | 4.8 | $0.398 | 0/3 | 14.4s |
| #123 | Muse Glimmer 30B high | Meta | 1 | 6.1 | $0.397 | 1/3 | 64.8s |
| #214 | GPT-5.4 none | OpenAI | 1 | 5.6 | $0.397 | 1/3 | 1.44s |
| #181 | Mimo V2 PRO medium | Xiaomi | 1 | 6.4 | $0.333 | 1/3 | 5.08s |
| #90 | GLM 5 Turbo medium | Z.ai | 1 | 8.7 | $0.323 | 2/3 | 5.23s |
| #223 | Qwen3.5-122B-A10B none | Qwen | 1 | 3.8 | $0.283 | 0/3 | 1.00s |
| #62 | GPT-5 Mini medium | OpenAI | 1 | 5.6 | $0.241 | 1/3 | 15.2s |
| #82 | Seed-2.0-Lite medium | Bytedance Seed | 1 | 9.0 | $0.236 | 2/3 | 10.2s |
| #222 | Kimi K2.6 none | Moonshot AI | 1 | 3.1 | $0.233 | 0/3 | 1.40s |
| #152 | MiMo-V2.5-Pro medium | Xiaomi | 1 | 6.7 | $0.221 | 1/3 | 5.31s |
| #264 | MiniMax M2.7 medium | Minimax | 1 | 5.9 | $0.208 | 1/3 | 24.9s |
| #193 | Inkling low | Thinkingmachines | 1 | 6.4 | $0.187 | 1/3 | 2.97s |