反AI技巧：答案错误
反AI技巧
答案错误
看看哪些 AI 模型在 反AI技巧 上最容易遇到 答案错误，更快找出薄弱点。 排序方式: 失败次数 ↑.
140/140
筛选模型
没有模型匹配当前搜索和筛选条件。
| 排名 | 模型 | 公司 | 答案错误 次数 | 分类得分 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #3 | GPT-5.6 Sol low | OpenAI | 1 | 8.3 | $0.971 | 3/4 | 2.60s |
| #5 | GPT-5.6 Sol high | OpenAI | 1 | 8.7 | $1.234 | 3/4 | 3.39s |
| #13 | GPT-5.3-Codex medium | OpenAI | 1 | 8.7 | $0.920 | 3/4 | 4.16s |
| #15 | Claude Opus 4.7 medium | Anthropic | 1 | 8.3 | $1.477 | 3/4 | 1.85s |
| #18 | GPT-5.4 medium | OpenAI | 1 | 8.3 | $1.533 | 3/4 | 4.11s |
| #21 | GPT-5.2 medium | OpenAI | 1 | 6.5 | $0.951 | 2/4 | 7.81s |
| #25 | Gemini 2.5 Flash medium | 1 | 8.4 | $0.643 | 3/4 | 6.30s | |
| #26 | GPT-5 Mini medium | OpenAI | 1 | 7.1 | $0.237 | 2/4 | 13.9s |
| #27 | Muse Spark 1.1 high | Meta | 1 | 7.5 | $1.694 | 2/4 | 8.60s |
| #30 | GPT-5.2 Chat none | OpenAI | 1 | 8.7 | $0.604 | 3/4 | 3.40s |
| #34 | GPT-5.6 Terra high | OpenAI | 1 | 8.3 | $1.055 | 3/4 | 2.54s |
| #35 | Seed-2.0-Lite medium | Bytedance Seed | 1 | 8.3 | $0.234 | 3/4 | 18.0s |
| #39 | GPT-5.6 Terra medium | OpenAI | 1 | 8.3 | $0.676 | 3/4 | 2.22s |
| #40 | Claude Sonnet 4.6 medium | Anthropic | 1 | 6.5 | $2.057 | 2/4 | 2.98s |
| #44 | GPT-5.6 Luna high | OpenAI | 1 | 8.3 | $1.017 | 3/4 | 2.99s |