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: Metric ↑.
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) |
|---|---|---|---|---|---|---|---|
| #182 | GLM 4.7 Flash none | Z.ai | 5.2 | 4.9 | $0.016 | 1/4 | 5.51s |
| #188 | KAT-Coder-Air V2.5 none | Kwaipilot | 5.3 | 4.8 | $0.067 | 1/4 | 2.68s |
| #166 | Laguna XS 2.1 none | Poolside | 5.3 | 5.3 | $0.008 | 1/4 | 755ms |
| #118 | Claude Sonnet 5 none | Anthropic | 5.3 | 6.3 | $0.548 | 1/4 | 3.60s |
| #51 | MiniMax M3 medium | Minimax | 5.5 | 7.6 | $0.286 | 1/4 | 14.9s |
| #173 | Mistral Small 4 medium | Mistral | 5.6 | 5.1 | $0.096 | 1/4 | 2.67s |
| #50 | DeepSeek V4 Pro high | DeepSeek | 5.7 | 7.7 | $0.200 | 1/4 | 25.7s |
| #47 | Claude Opus 4.6 medium | Anthropic | 6.4 | 7.7 | $3.059 | 2/4 | 7.45s |
| #141 | Hy3 preview high | Tencent | 6.4 | 5.9 | $0.048 | 2/4 | 15.1s |
| #213 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 6.4 | 3.4 | $0.000 | 2/4 | 1.20s |
| #134 | GPT-5 Nano medium | OpenAI | 6.5 | 6.1 | $0.114 | 2/4 | 25.5s |
| #44 | Claude Sonnet 4.6 medium | Anthropic | 6.5 | 7.8 | $2.057 | 2/4 | 2.98s |
| #63 | Qwen3.7 Max none | Qwen | 6.5 | 7.4 | $0.197 | 2/4 | 1.08s |
| #70 | Claude Opus 4.8 none | Anthropic | 6.5 | 7.3 | $1.166 | 2/4 | 3.40s |
| #75 | Qwen3.7 Plus none | Qwen | 6.5 | 7.2 | $0.106 | 2/4 | 1.38s |