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: Response Time (avg) ↑.
Failure Reasons
| Rank | Model | Company | Did not follow instructions Count | Category Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #22 | Step 3.7 Flash medium | Stepfun | 1 | 8.7 | 3/4 | 9.65s |
| #99 | gpt-oss-120b medium | OpenAI | 1 | 6.7 | 2/4 | 10.2s |
| #59 | GLM 5V Turbo medium | Z.ai | 1 | 7.2 | 2/4 | 10.8s |
| #156 | Hy3 preview none | Tencent | 2 | 4.8 | 1/4 | 11.1s |
| #60 | Kimi K2.6 medium | Moonshot AI | 1 | 7.0 | 2/4 | 11.6s |
| #138 | Ling-2.6-flash none | Inclusionai | 1 | 6.8 | 2/4 | 11.8s |
| #54 | GPT-5 Mini medium | OpenAI | 1 | 7.1 | 2/4 | 13.9s |
| #113 | DeepSeek V4 Pro none | DeepSeek | 1 | 3.5 | 0/4 | 14.0s |
| #67 | MiniMax M3 medium | Minimax | 1 | 5.5 | 1/4 | 14.9s |
| #158 | GLM 4.7 Flash medium | Z.ai | 1 | 4.7 | 1/4 | 15.0s |
| #129 | MiniMax M2.5 medium | Minimax | 1 | 7.9 | 2/4 | 20.8s |
| #126 | gpt-oss-120b none | OpenAI | 1 | 6.5 | 2/4 | 32.8s |
| #130 | MiniMax M2.7 medium | Minimax | 1 | 7.9 | 2/4 | 40.3s |
| #96 | Ring-2.6-1T none | Inclusionai | 1 | 9.2 | 3/4 | 43.3s |