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) |
|---|---|---|---|---|---|---|---|
| #178 | MiMo-V2.6-Flash low | Xiaomi | 1 | 0.8 | $0.200 | 3/4 | 1.51s |
| #152 | GLM 5.3 FlashX high | Z.ai | 1 | 0.8 | $0.210 | 3/4 | 1.98s |
| #227 | GLM 5.3 low | Z.ai | 2 | 0.7 | $0.215 | 2/4 | 4.16s |
| #270 | Qwen3.5 Plus 2026-04-20 none | Qwen | 3 | 0.5 | $0.216 | 1/4 | 1.88s |
| #121 | MiMo-V2.6-Flash medium | Xiaomi | 2 | 0.6 | $0.218 | 1/4 | 1.42s |
| #189 | Muse Glimmer 30B low | Meta | 1 | 0.9 | $0.219 | 3/4 | 3.57s |
| #325 | Qwen3.6 Max Preview none | Qwen | 3 | 0.5 | $0.228 | 1/4 | 2.63s |
| #110 | GPT-5.4 Nano medium | OpenAI | 1 | 0.8 | $0.235 | 3/4 | 4.52s |
| #215 | GLM 5.2 none | Z.ai | 1 | 0.8 | $0.250 | 3/4 | 3.70s |
| #313 | Seed-2.0-Code none | Bytedance Seed | 2 | 0.3 | $0.257 | 0/4 | 5.06s |
| #106 | DeepSeek V4 Flash 0423 high | DeepSeek | 1 | 0.8 | $0.261 | 3/4 | 28.5s |
| #324 | Kimi K2.5 none | Moonshot AI | 4 | 0.4 | $0.262 | 0/4 | 6.24s |
| #102 | Seed-2.0-Lite medium | Bytedance Seed | 1 | 0.8 | $0.271 | 3/4 | 18.0s |
| #138 | Muse Glimmer 30B medium | Meta | 1 | 0.9 | $0.288 | 3/4 | 7.36s |
| #295 | Mistral Large 4 none | Mistral | 4 | 0.4 | $0.290 | 0/4 | 1.59s |