AI BENCHY Category Failures
Anti-AI Tricks
Did not follow instructions
Anti-AI Tricks
Did not follow instructions
See which AI models are most likely to hit Did not follow instructions on Anti-AI Tricks, so you can spot weak points faster. Sort by: Failure Count ↑.
Related Failure Reasons
Related Categories
| Rank | Model | Company | Did not follow instructions Count | Category Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #12 | Gemini 3.1 Flash Lite Preview medium | 1 | 9.0 | 2/3 | 2.53s | |
| #19 | GPT-5.3 Chat none | OpenAI | 1 | 7.3 | 2/3 | 4.72s |
| #22 | Gemini 3.1 Flash Lite Preview none | 1 | 6.0 | 1/3 | 1.16s | |
| #27 | GPT-5.2 medium | OpenAI | 1 | 7.0 | 2/3 | 14.3s |
| #32 | GPT-5 Mini medium | OpenAI | 1 | 7.0 | 2/3 | 16.5s |
| #36 | Mercury 2 medium | Inception | 1 | 7.3 | 2/3 | 1.30s |
| #39 | gpt-oss-120b medium | OpenAI | 1 | 7.0 | 2/3 | 19.8s |
| #43 | MiniMax M2.5 medium | Minimax | 1 | 9.3 | 2/3 | 32.4s |
| #48 | Qwen3 Coder Next none | Qwen | 1 | 2.3 | 0/3 | 4.39s |
| #50 | Qwen3 Coder Next medium | Qwen | 1 | 1.3 | 0/3 | 15.3s |
| #52 | GLM 4.7 Flash medium | Z.ai | 1 | 4.0 | 1/3 | 27.1s |
| #53 | Grok 4.1 Fast none | X AI | 1 | 1.3 | 0/3 | 1.73s |