答案错误 失败
看看哪些 AI 模型最常遇到 答案错误，让你在选择前先发现稳定性风险。 排序方式: 分数 ↑.
313/313
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 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #15 | GPT-5.6 Sol high | OpenAI | 4 | 9.4 | $0.446 | 18/22 | 11.5s |
| #14 | GPT-6 Astra medium | OpenAI | 3 | 9.4 | $1.774 | 19/22 | 8.08s |
| #13 | GPT-5.6 Sol medium | OpenAI | 4 | 9.4 | $0.508 | 18/22 | 12.6s |
| #12 | Gemini 3.7 Flash medium | 2 | 9.4 | $0.309 | 20/22 | 5.87s | |
| #11 | Gemini 3.5 Flash high | 2 | 9.4 | $2.011 | 19/22 | 15.5s | |
| #10 | Gemini 3 Flash Preview medium | 2 | 9.5 | $0.763 | 20/22 | 19.9s | |
| #9 | GPT-6 Astra low | OpenAI | 2 | 9.5 | $1.289 | 20/22 | 5.09s |
| #8 | GPT-5.6 Sol low | OpenAI | 4 | 9.5 | $0.357 | 18/22 | 9.04s |
| #6 | Gemini 3.7 Flash high | 2 | 9.8 | $0.646 | 20/22 | 12.2s | |
| #7 | Gemini 3.6 Flash medium | 2 | 9.8 | $0.427 | 20/22 | 11.9s | |
| #4 | GPT-6 Astra high | OpenAI | 1 | 9.9 | $3.474 | 21/22 | 18.6s |
| #5 | GPT-6 Astra xhigh | OpenAI | 1 | 9.9 | $5.156 | 21/22 | 28.4s |
| #1 | Gemini 3.6 Flash high | 1 | 9.9 | $0.699 | 21/22 | 16.8s |