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: 失败次数 ↑.
| 排名 | 模型 | 公司 | 超时 次数 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #150 | Qwen3 Coder Next medium | Qwen | 1 | 4.6 | 4/21 | 8.58s |
| #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 |
| #37 | Gemma 4 26B A4B medium | 2 | 7.6 | 14/21 | 63.4s | |
| #55 | GLM 5.1 medium | Z.ai | 2 | 7.3 | 12/21 | 33.7s |
| #72 | DeepSeek V3.2 medium | DeepSeek | 2 | 7.0 | 11/21 | 68.7s |
| #76 | Kimi K2.5 medium | Moonshot AI | 2 | 6.8 | 10/21 | 98.4s |
| #79 | Hunter Alpha medium | OpenRouter | 2 | 6.7 | 8/18 | 10.3s |
| #130 | MiniMax M2.7 medium | Minimax | 2 | 5.3 | 5/21 | 38.2s |
| #158 | GLM 4.7 Flash medium | Z.ai | 2 | 4.4 | 4/21 | 35.1s |
| #49 | Qwen3.5-Flash medium | Qwen | 3 | 7.4 | 12/21 | 63.3s |
| #60 | Kimi K2.6 medium | Moonshot AI | 3 | 7.2 | 12/21 | 71.7s |
| #67 | MiniMax M3 medium | Minimax | 3 | 7.1 | 11/21 | 68.2s |
| #103 | DeepSeek V4 Pro high | DeepSeek | 3 | 6.0 | 8/21 | 65.2s |