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: 测试正确 ↑.
215/215
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） |
|---|---|---|---|---|---|---|---|
| #40 | Qwen3.7 Plus medium | Qwen | 5 | 7.9 | $0.267 | 15/22 | 51.5s |
| #41 | Qwen3.6 Plus medium | Qwen | 5 | 7.8 | $0.405 | 15/22 | 43.1s |
| #48 | GPT-5.6 Luna high | OpenAI | 7 | 7.7 | $1.017 | 15/22 | 18.7s |
| #63 | Qwen3.7 Max none | Qwen | 7 | 7.4 | $0.197 | 15/22 | 4.52s |
| #83 | Gemini 3.5 Flash none | 3 | 7.0 | $1.079 | 15/22 | 9.93s | |
| #42 | GLM 5.2 medium | Z.ai | 3 | 7.8 | $0.187 | 15/21 | 23.3s |
| #46 | GLM 5 medium | Z.ai | 3 | 7.7 | $0.307 | 15/21 | 33.5s |
| #16 | GPT-5.3-Codex medium | OpenAI | 4 | 8.9 | $0.920 | 16/22 | 17.0s |
| #22 | Qwen3.6 Max Preview medium | Qwen | 5 | 8.4 | $1.143 | 16/22 | 67.5s |
| #23 | Grok 4.5 low | X AI | 6 | 8.4 | $0.935 | 16/22 | 15.6s |
| #25 | Grok 4.5 medium | X AI | 6 | 8.3 | $1.928 | 16/22 | 61.7s |
| #26 | Claude Sonnet 5 medium | Anthropic | 4 | 8.3 | $0.922 | 16/22 | 12.5s |
| #45 | Claude Opus 4.8 low | Anthropic | 4 | 7.8 | $2.077 | 16/22 | 12.7s |
| #65 | Gemini 3 Flash Preview low | 6 | 7.4 | $0.177 | 16/22 | 6.28s | |
| #15 | Grok 4.5 high | X AI | 2 | 8.9 | $1.707 | 17/22 | 76.5s |