General Intelligence: Did not follow instructions
General Intelligence
Did not follow instructions
See which AI models are most likely to hit Did not follow instructions on General Intelligence, so you can spot weak points faster. Sort by: Tests Correct ↑.
Failure Reasons
78/78
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) |
|---|---|---|---|---|---|---|---|
| #12 | Grok 4.5 high | X AI | 1 | 4.7 | $1.707 | 0/1 | 9.82s |
| #13 | GPT-5.3-Codex medium | OpenAI | 1 | 4.6 | $0.920 | 0/1 | 4.87s |
| #18 | GPT-5.4 medium | OpenAI | 1 | 4.7 | $1.533 | 0/1 | 4.92s |
| #21 | GPT-5.2 medium | OpenAI | 1 | 3.7 | $0.951 | 0/1 | 4.32s |
| #23 | Claude Sonnet 5 medium | Anthropic | 1 | 4.8 | $0.922 | 0/1 | 4.32s |
| #25 | Gemini 2.5 Flash medium | 1 | 4.8 | $0.643 | 0/1 | 4.86s | |
| #26 | GPT-5 Mini medium | OpenAI | 1 | 4.5 | $0.237 | 0/1 | 13.5s |
| #30 | GPT-5.2 Chat none | OpenAI | 1 | 4.4 | $0.604 | 0/1 | 3.20s |
| #35 | Seed-2.0-Lite medium | Bytedance Seed | 1 | 6.7 | $0.234 | 0/1 | 18.2s |
| #37 | Qwen3.6 Plus medium | Qwen | 1 | 5.1 | $0.405 | 0/1 | 27.1s |
| #42 | GLM 5 medium | Z.ai | 1 | 6.1 | $0.307 | 0/1 | 14.7s |
| #45 | DeepSeek V4 Flash high | DeepSeek | 1 | 6.1 | $0.042 | 0/1 | 25.2s |
| #47 | MiniMax M3 medium | Minimax | 1 | 5.1 | $0.286 | 0/1 | 33.3s |
| #53 | GPT-5.4 Nano medium | OpenAI | 1 | 4.5 | $0.138 | 0/1 | 4.15s |
| #54 | GPT-5.3 Chat none | OpenAI | 1 | 4.6 | $0.571 | 0/1 | 1.99s |