AI BENCHY Failures
Did not follow instructions Failures
See which AI models run into Did not follow instructions most often, so you can spot reliability risks before choosing one. Sort by: Response Time (avg) ↑.
| Rank | Model | Company | Did not follow instructions Count | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #55 | MiMo-V2-Omni none | Xiaomi | 2 | 6.5 | 8/18 | 1.99s |
| #89 | GPT-4o-mini none | OpenAI | 1 | 4.9 | 4/18 | 2.00s |
| #69 | Kimi K2.6 none | Moonshot AI | 3 | 5.8 | 7/18 | 2.05s |
| #54 | Mercury 2 medium | Inception | 4 | 6.5 | 8/18 | 2.21s |
| #65 | MiMo-V2-Pro none | Xiaomi | 2 | 6.0 | 7/18 | 2.39s |
| #94 | MiMo-V2-Flash none | Xiaomi | 1 | 4.5 | 3/18 | 2.79s |
| #77 | GLM 5 Turbo none | Z.ai | 2 | 5.5 | 6/18 | 2.94s |
| #58 | GLM 5V Turbo none | Z.ai | 2 | 6.2 | 8/18 | 3.10s |
| #22 | Gemini 3.1 Flash Lite Preview low | 1 | 8.1 | 13/18 | 3.22s | |
| #59 | Qwen3.5-Flash none | Qwen | 1 | 6.2 | 8/18 | 3.25s |
| #74 | GLM 4.7 Flash none | Z.ai | 2 | 5.6 | 5/18 | 3.35s |
| #70 | Qwen3.5-122B-A10B none | Qwen | 1 | 5.7 | 6/18 | 3.69s |
| #17 | Gemini 3.1 Flash Lite Preview medium | 1 | 8.2 | 13/18 | 3.74s | |
| #63 | Qwen3.5-35B-A3B none | Qwen | 2 | 6.1 | 7/18 | 3.82s |
| #48 | Gemma 4 31B none | 1 | 6.9 | 10/18 | 4.02s |