AI BENCHY Category Failures
Anti-AI Tricks: Wrong answer
Anti-AI Tricks
Wrong answer
See which AI models are most likely to hit Wrong answer on Anti-AI Tricks, so you can spot weak points faster. Sort by: Tests Correct ↓.
Failure Reasons
| Rank | Model | Company | Wrong answer Count | Category Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #74 | GLM 4.7 Flash none | Z.ai | 3 | 5.2 | 1/4 | 5.51s |
| #82 | Grok 4.20 none | X AI | 3 | 4.8 | 1/4 | 501ms |
| #88 | Nemotron 3 Super none | NVIDIA | 3 | 4.8 | 1/4 | 7.43s |
| #89 | GPT-4o-mini none | OpenAI | 3 | 4.8 | 1/4 | 1.34s |
| #93 | GLM 4.7 Flash medium | Z.ai | 2 | 4.7 | 1/4 | 15.0s |
| #97 | Qwen3.5-9B medium | Qwen | 1 | 5.1 | 1/4 | 34.4s |
| #59 | Qwen3.5-Flash none | Qwen | 4 | 3.5 | 0/4 | 1.32s |
| #61 | Seed-2.0-Lite none | Bytedance Seed | 4 | 3.0 | 0/4 | 2.43s |
| #62 | Gemini 2.5 Flash none | 4 | 3.0 | 0/4 | 582ms | |
| #63 | Qwen3.5-35B-A3B none | Qwen | 4 | 3.4 | 0/4 | 1.43s |
| #64 | DeepSeek V3.2 none | DeepSeek | 2 | 3.2 | 0/4 | 7.63s |
| #65 | MiMo-V2-Pro none | Xiaomi | 4 | 3.5 | 0/4 | 1.80s |
| #66 | GPT-5.4 none | OpenAI | 4 | 3.2 | 0/4 | 1.21s |
| #72 | Hunter Alpha none | OpenRouter | 4 | 3.5 | 0/4 | 3.81s |
| #75 | GLM 5.1 none | Z.ai | 4 | 4.0 | 0/4 | 2.11s |