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) |
|---|---|---|---|---|---|---|
| #114 | Qwen3.5 Plus 2026-04-20 none | Qwen | 2 | 5.7 | 7/21 | 4.39s |
| #85 | Gemma 4 31B none | 1 | 6.5 | 10/21 | 4.05s | |
| #40 | Gemini 3.1 Flash Lite Preview medium | 1 | 7.5 | 13/21 | 3.96s | |
| #153 | Qwen3.6 35B A3B none | Qwen | 2 | 4.6 | 4/21 | 3.73s |
| #118 | Qwen3.6 27B none | Qwen | 2 | 5.6 | 7/21 | 3.72s |
| #68 | Claude Opus 4.8 none | Anthropic | 1 | 7.0 | 12/21 | 3.47s |
| #131 | Qwen3.5-122B-A10B none | Qwen | 2 | 5.3 | 6/21 | 3.41s |
| #117 | Qwen3.5-35B-A3B none | Qwen | 2 | 5.6 | 7/21 | 3.37s |
| #44 | Gemini 3.1 Flash Lite medium | 1 | 7.5 | 13/21 | 3.23s | |
| #109 | GLM 5V Turbo none | Z.ai | 2 | 5.8 | 8/21 | 2.99s |
| #151 | Trinity Large Preview none | Arcee AI | 3 | 4.6 | 4/21 | 2.98s |
| #122 | GLM 4.7 Flash none | Z.ai | 1 | 5.5 | 6/21 | 2.86s |
| #88 | Qwen3.7 Plus none | Qwen | 1 | 6.4 | 10/21 | 2.85s |
| #134 | GLM 5 Turbo none | Z.ai | 2 | 5.2 | 6/21 | 2.82s |
| #50 | Gemini 3.1 Flash Lite Preview low | 1 | 7.4 | 13/21 | 2.77s |