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: Response Time (avg) ↑.
Failure Reasons
| Rank | Model | Company | Wrong answer Count | Category Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #94 | MiMo-V2-Flash none | Xiaomi | 4 | 3.2 | 0/4 | 1.19s |
| #66 | GPT-5.4 none | OpenAI | 4 | 3.2 | 0/4 | 1.21s |
| #21 | Gemini 3 Flash Preview none | 1 | 8.3 | 3/4 | 1.25s | |
| #60 | Gemma 4 26B A4B none | 1 | 8.3 | 3/4 | 1.28s | |
| #59 | Qwen3.5-Flash none | Qwen | 4 | 3.5 | 0/4 | 1.32s |
| #89 | GPT-4o-mini none | OpenAI | 3 | 4.8 | 1/4 | 1.34s |
| #69 | Kimi K2.6 none | Moonshot AI | 3 | 4.6 | 1/4 | 1.39s |
| #63 | Qwen3.5-35B-A3B none | Qwen | 4 | 3.4 | 0/4 | 1.43s |
| #70 | Qwen3.5-122B-A10B none | Qwen | 3 | 4.8 | 1/4 | 1.59s |
| #90 | Qwen3.5-9B none | Qwen | 4 | 3.1 | 0/4 | 1.71s |
| #65 | MiMo-V2-Pro none | Xiaomi | 4 | 3.5 | 0/4 | 1.80s |
| #3 | Claude Opus 4.7 medium | Anthropic | 1 | 8.3 | 3/4 | 1.85s |
| #48 | Gemma 4 31B none | 2 | 6.5 | 2/4 | 1.85s | |
| #49 | Qwen3.5 Plus 2026-02-15 none | Qwen | 3 | 4.8 | 1/4 | 1.91s |
| #75 | GLM 5.1 none | Z.ai | 4 | 4.0 | 0/4 | 2.11s |