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: Total Cost ↑.
Failure Reasons
249/249
Filter models
No models match the current search and filters.
| Rank | Model | Company | Wrong answer Count | Category Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #88 | DeepSeek V4 Flash 0731 high | DeepSeek | 1 | 0.9 | $0.576 | 3/4 | 13.6s |
| #67 | MiMo-V2.6-Pro medium | Xiaomi | 1 | 0.7 | $0.586 | 2/4 | 2.76s |
| #63 | DeepSeek V4.1 Flash medium | DeepSeek | 1 | 0.8 | $0.591 | 3/4 | 3.07s |
| #180 | GPT-5.2 Chat default | OpenAI | 1 | 0.9 | $0.594 | 3/4 | 3.40s |
| #62 | DeepSeek V4.1 Flash high | DeepSeek | 1 | 0.8 | $0.617 | 3/4 | 3.42s |
| #275 | Claude Sonnet 4.6 none | Anthropic | 1 | 0.5 | $0.661 | 1/4 | 2.94s |
| #260 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 1 | 0.8 | $0.669 | 3/4 | 3.90s |
| #161 | Gemini 2.5 Flash medium | 1 | 0.8 | $0.680 | 3/4 | 6.30s | |
| #226 | Beam 1.0 501B A23B xhigh | Reflection | 1 | 0.9 | $0.688 | 3/4 | 1.52s |
| #300 | GPT-5.4 none | OpenAI | 4 | 0.3 | $0.690 | 0/4 | 1.21s |
| #90 | GPT-5.6 Terra high | OpenAI | 1 | 0.8 | $0.698 | 3/4 | 2.54s |
| #249 | Gemini 3.1 Flash Lite low | 2 | 0.7 | $0.717 | 2/4 | 1.84s | |
| #248 | Gemini 3.1 Flash Lite Preview low | 1 | 0.8 | $0.736 | 3/4 | 2.12s | |
| #273 | KAT-Coder-Pro V2.5 default | Kwaipilot | 1 | 0.9 | $0.742 | 3/4 | 4.58s |
| #346 | Grok 4.20 Beta medium | X AI | 1 | 0.9 | $0.750 | 3/4 | 3.16s |