AI BENCHY Category Failures
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: Response Time (avg) ↓.
Failure Reasons
| Rank | Model | Company | Wrong answer Count | Category Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #73 | Seed-2.0-Mini medium | Bytedance Seed | 1 | 6.6 | 2/4 | 74.7s |
| #76 | Kimi K2.5 medium | Moonshot AI | 1 | 7.3 | 2/4 | 51.4s |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 1 | 8.2 | 3/4 | 45.8s |
| #130 | MiniMax M2.7 medium | Minimax | 1 | 7.9 | 2/4 | 40.3s |
| #53 | Gemini 3.1 Flash Lite high | 1 | 8.7 | 3/4 | 37.2s | |
| #161 | Qwen3.5-9B medium | Qwen | 1 | 5.1 | 1/4 | 34.4s |
| #126 | gpt-oss-120b none | OpenAI | 1 | 6.5 | 2/4 | 32.8s |
| #31 | DeepSeek V4 Flash high | DeepSeek | 1 | 8.3 | 3/4 | 28.5s |
| #94 | GPT-5 Nano medium | OpenAI | 2 | 6.5 | 2/4 | 25.5s |
| #139 | DeepSeek V4 Flash none | DeepSeek | 4 | 3.0 | 0/4 | 20.2s |
| #19 | Seed-2.0-Lite medium | Bytedance Seed | 1 | 8.3 | 3/4 | 18.0s |
| #103 | DeepSeek V4 Pro high | DeepSeek | 1 | 6.4 | 2/4 | 16.5s |
| #158 | GLM 4.7 Flash medium | Z.ai | 2 | 4.7 | 1/4 | 15.0s |
| #67 | MiniMax M3 medium | Minimax | 2 | 5.5 | 1/4 | 14.9s |
| #113 | DeepSeek V4 Pro none | DeepSeek | 3 | 3.5 | 0/4 | 14.0s |