额外格式 失败
看看哪些 AI 模型最常遇到 额外格式，让你在选择前先发现稳定性风险。 排序方式: 总成本 ↓.
42/42
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 | 额外格式 次数 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #47 | MiniMax M3 medium | Minimax | 1 | 7.6 | $0.286 | 12/22 | 75.0s |
| #46 | DeepSeek V4 Pro high | DeepSeek | 1 | 7.7 | $0.200 | 10/22 | 79.1s |
| #84 | MiMo-V2.5-Pro medium | Xiaomi | 3 | 6.9 | $0.187 | 12/22 | 33.9s |
| #164 | Inkling none | Thinkingmachines | 1 | 5.2 | $0.147 | 6/22 | 3.50s |
| #159 | GPT-5.6 Luna none | OpenAI | 1 | 5.4 | $0.142 | 6/22 | 1.50s |
| #82 | DeepSeek V4 Pro none | DeepSeek | 1 | 6.9 | $0.096 | 10/22 | 11.6s |
| #101 | MiMo-V2.5 medium | Xiaomi | 2 | 6.5 | $0.082 | 12/22 | 32.2s |
| #144 | KAT-Coder-Air V2.5 high | Kwaipilot | 3 | 5.6 | $0.077 | 7/22 | 15.9s |
| #182 | KAT-Coder-Air V2.5 none | Kwaipilot | 3 | 4.8 | $0.067 | 5/22 | 12.2s |
| #197 | Grok 4.20 none | X AI | 1 | 4.1 | $0.057 | 6/18 | 1.11s |
| #173 | DeepSeek V3.2 none | DeepSeek | 2 | 5.0 | $0.054 | 6/22 | 18.3s |
| #149 | KAT-Coder-Air V2.5 medium | Kwaipilot | 1 | 5.6 | $0.048 | 8/22 | 8.42s |
| #111 | LongCat 2.0 none | Meituan | 1 | 6.3 | $0.044 | 7/22 | 5.18s |
| #150 | DeepSeek V4 Flash none | DeepSeek | 2 | 5.6 | $0.044 | 5/22 | 36.8s |
| #113 | MiMo-V2-Flash medium | Xiaomi | 1 | 6.3 | $0.043 | 12/21 | 20.1s |