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
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) |
|---|---|---|---|---|---|---|---|
| #421 | d1-ultra default | Liquid | 2 | 0.4 | $0.003 | 1/3 | 432ms |
| #423 | Jev 1.13 default | Typesafe | 2 | 0.4 | $0.003 | 1/3 | 853ms |
| #425 | Decider V1.1 27B default | Perplexity | 2 | 0.4 | $0.002 | 1/3 | 321ms |
| #426 | Drex v1.5 default | Nace AI | 2 | 0.4 | $0.002 | 1/3 | 871ms |
| #429 | Jev 1.14 default | Typesafe | 2 | 0.4 | $0.003 | 1/3 | 300ms |
| #430 | Classify-1 default | Scaledown | 2 | 0.4 | $0.008 | 1/3 | 3.69s |
| #431 | Clef Omni default | Cloudflare | 2 | 0.4 | $0.011 | 1/3 | 861ms |
| #432 | Decider Flash V1.2 default | Perplexity | 2 | 0.4 | $0.001 | 1/3 | 466ms |
| #434 | D1 default | Liquid | 2 | 0.4 | $0.003 | 1/3 | 431ms |
| #438 | Microsoft-Decision-1 default | Microsoft | 2 | 0.4 | $0.002 | 1/3 | 992ms |
| #104 | DeepSeek V4 Pro 0423 high | DeepSeek | 2 | 0.6 | $0.149 | 1/4 | 25.7s |
| #121 | MiMo-V2.6-Flash medium | Xiaomi | 2 | 0.6 | $0.218 | 1/4 | 1.42s |
| #165 | Qwen3.5-27B none | Qwen | 3 | 0.5 | $0.116 | 1/4 | 788ms |
| #175 | Claude Opus 5 none | Anthropic | 3 | 0.6 | $2.766 | 1/4 | 4.33s |
| #208 | MiniMax M3 medium | Minimax | 2 | 0.6 | $0.422 | 1/4 | 14.9s |