Anti-AI Tricks Ranking
See which AI models perform best on Anti-AI Tricks, which ones stay reliable, and where the biggest gaps appear. Sort by: Total Cost ↑.
216/216
Filter models
No models match the current search and filters.
| Rank | Model | Company | Anti-AI Tricks Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #61 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 8.2 | 7.5 | $0.437 | 3/4 | 45.8s |
| #71 | Step 3.7 Flash low | Stepfun | 8.7 | 7.3 | $0.454 | 3/4 | 4.02s |
| #98 | GLM 5V Turbo medium | Z.ai | 7.2 | 6.7 | $0.457 | 2/4 | 10.8s |
| #85 | KAT-Coder-Pro V2.5 medium | Kwaipilot | 8.2 | 6.9 | $0.467 | 3/4 | 3.90s |
| #102 | LongCat 2.0 high | Meituan | 8.9 | 6.6 | $0.469 | 3/4 | 7.76s |
| #97 | KAT-Coder-Pro V2.5 none | Kwaipilot | 8.7 | 6.7 | $0.476 | 3/4 | 4.58s |
| #64 | LongCat 2.0 medium | Meituan | 10.0 | 7.4 | $0.478 | 4/4 | 9.65s |
| #73 | KAT-Coder-Pro V2.5 high | Kwaipilot | 7.0 | 7.2 | $0.482 | 2/4 | 3.17s |
| #99 | Claude Opus 4.7 none | Anthropic | 8.3 | 6.6 | $0.505 | 3/4 | 2.12s |
| #33 | Step 3.7 Flash medium | Stepfun | 8.7 | 8.0 | $0.515 | 3/4 | 9.65s |
| #6 | Gemini 3.6 Flash low | 10.0 | 9.4 | $0.517 | 4/4 | 1.66s | |
| #59 | GPT-5.6 Terra low | OpenAI | 8.3 | 7.5 | $0.519 | 3/4 | 2.36s |
| #87 | GPT-5.6 Sol none | OpenAI | 8.3 | 6.9 | $0.524 | 3/4 | 1.27s |
| #78 | GLM 5.1 medium | Z.ai | 10.0 | 7.1 | $0.535 | 4/4 | 8.31s |
| #91 | GPT-5.5 none | OpenAI | 6.9 | 6.9 | $0.544 | 2/4 | 1.31s |