超时 失败
看看哪些 AI 模型最常遇到 超时，让你在选择前先发现稳定性风险。 排序方式: 失败次数 ↑.
67/67
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 | 超时 次数 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #136 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 1 | 0.8 | $0.435 | 14/23 | 54.1s |
| #146 | Mistral Large 4 high | Mistral | 1 | 0.8 | $1.391 | 12/23 | 263.7s |
| #171 | LongCat 2.0 medium | Meituan | 1 | 0.7 | $0.767 | 12/23 | 144.9s |
| #172 | GLM 5 medium | Z.ai | 1 | 0.7 | $0.479 | 15/22 | 39.0s |
| #181 | Qwen3.6 Max Preview medium | Qwen | 1 | 0.7 | $1.132 | 17/22 | 66.5s |
| #192 | Gemma 4 31B medium | 1 | 0.7 | $0.144 | 14/23 | 78.8s | |
| #206 | Solar Pro 4 low | Upstage | 1 | 0.7 | $0.101 | 11/23 | 145.2s |
| #217 | LongCat 2.0 low | Meituan | 1 | 0.7 | $0.630 | 10/23 | 115.0s |
| #224 | Mercury 2.5 Preview high | Inception | 1 | 0.6 | $0.040 | 12/23 | 7.61s |
| #236 | Claude Sonnet 4.6 medium | Anthropic | 1 | 0.6 | $2.126 | 14/22 | 28.1s |
| #239 | Mercury 2.5 medium | Inception | 1 | 0.6 | $0.034 | 12/23 | 7.74s |
| #261 | GLM 5 Turbo medium | Z.ai | 1 | 0.6 | $0.323 | 14/21 | 23.0s |
| #293 | GPT-5 Nano medium | OpenAI | 1 | 0.6 | $0.159 | 8/23 | 56.5s |
| #305 | Nemotron 3.5 Super VL none | NVIDIA | 1 | 0.6 | $0.040 | 8/23 | 47.0s |
| #306 | Nemotron 3 Super medium | NVIDIA | 1 | 0.6 | $0.081 | 8/23 | 56.4s |