AI BENCHY Category Failures
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
| Rank | Model | Company | Did not follow instructions Count | Category Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #57 | GPT-5 Nano medium | OpenAI | 1 | 4.1 | 0/1 | 17.5s |
| #58 | GLM 5V Turbo none | Z.ai | 1 | 4.6 | 0/1 | 2.22s |
| #60 | Gemma 4 26B A4B none | 1 | 4.0 | 0/1 | 3.54s | |
| #63 | Qwen3.5-35B-A3B none | Qwen | 1 | 6.5 | 0/1 | 1.19s |
| #65 | MiMo-V2-Pro none | Xiaomi | 1 | 4.3 | 0/1 | 2.44s |
| #67 | Qwen3.5-27B none | Qwen | 1 | 5.0 | 0/1 | 2.51s |
| #68 | gpt-oss-120b medium | OpenAI | 1 | 4.3 | 0/1 | 7.90s |
| #69 | Kimi K2.6 none | Moonshot AI | 1 | 5.4 | 0/1 | 1.55s |
| #70 | Qwen3.5-122B-A10B none | Qwen | 1 | 5.0 | 0/1 | 1.12s |
| #71 | MiniMax M2.5 medium | Minimax | 1 | 3.8 | 0/1 | 6.63s |
| #72 | Hunter Alpha none | OpenRouter | 1 | 6.1 | 0/1 | 2.71s |
| #73 | Mistral Small 4 medium | Mistral | 1 | 4.8 | 0/1 | 2.05s |
| #77 | GLM 5 Turbo none | Z.ai | 1 | 4.2 | 0/1 | 2.18s |
| #78 | Trinity Large Preview none | Arcee AI | 1 | 4.4 | 0/1 | 2.86s |
| #79 | Grok 4.20 Beta none | X AI | 1 | 5.0 | 0/1 | 541ms |