AI BENCHY 失败分析
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: 测试正确 ↑.
| 排名 | 模型 | 公司 | 超时 次数 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #73 | Seed-2.0-Mini medium | Bytedance Seed | 5 | 6.9 | 11/21 | 80.2s |
| #62 | Step 3.5 Flash medium | Stepfun | 1 | 7.2 | 11/20 | 72.5s |
| #49 | Qwen3.5-Flash medium | Qwen | 3 | 7.4 | 12/21 | 63.3s |
| #51 | Mimo V2 PRO medium | Xiaomi | 1 | 7.4 | 12/21 | 22.2s |
| #54 | GPT-5 Mini medium | OpenAI | 1 | 7.3 | 12/21 | 23.6s |
| #55 | GLM 5.1 medium | Z.ai | 2 | 7.3 | 12/21 | 33.7s |
| #60 | Kimi K2.6 medium | Moonshot AI | 3 | 7.2 | 12/21 | 71.7s |
| #64 | MiMo-V2-Flash medium | Xiaomi | 1 | 7.2 | 12/21 | 20.1s |
| #30 | Qwen3.5-27B medium | Qwen | 1 | 7.8 | 13/21 | 68.4s |
| #42 | GPT-5.2 medium | OpenAI | 1 | 7.5 | 13/21 | 16.9s |
| #52 | Claude Sonnet 4.6 medium | Anthropic | 1 | 7.4 | 13/21 | 17.1s |
| #23 | GLM 5 Turbo medium | Z.ai | 1 | 8.0 | 14/21 | 23.0s |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 2 | 7.9 | 14/21 | 73.8s |
| #27 | Gemma 4 31B medium | 2 | 7.8 | 14/21 | 56.5s | |
| #29 | Qwen3.5-122B-A10B medium | Qwen | 2 | 7.8 | 14/21 | 42.5s |