AI BENCHY 失败分析
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: 响应时间（平均） ↑.
| 排名 | 模型 | 公司 | 答案错误 次数 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #103 | DeepSeek V4 Pro high | DeepSeek | 4 | 6.0 | 8/21 | 65.2s |
| #129 | MiniMax M2.5 medium | Minimax | 7 | 5.3 | 5/21 | 65.4s |
| #12 | Gemini 3.1 Flash Lite Preview high | 2 | 8.6 | 13/16 | 68.1s | |
| #67 | MiniMax M3 medium | Minimax | 3 | 7.1 | 11/21 | 68.2s |
| #30 | Qwen3.5-27B medium | Qwen | 4 | 7.8 | 13/21 | 68.4s |
| #72 | DeepSeek V3.2 medium | DeepSeek | 5 | 7.0 | 11/21 | 68.7s |
| #60 | Kimi K2.6 medium | Moonshot AI | 3 | 7.2 | 12/21 | 71.7s |
| #62 | Step 3.5 Flash medium | Stepfun | 4 | 7.2 | 11/20 | 72.5s |
| #66 | Qwen3.5-35B-A3B medium | Qwen | 2 | 7.1 | 11/21 | 72.6s |
| #25 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 4 | 7.9 | 14/21 | 73.8s |
| #73 | Seed-2.0-Mini medium | Bytedance Seed | 4 | 6.9 | 11/21 | 80.2s |
| #161 | Qwen3.5-9B medium | Qwen | 2 | 4.2 | 3/21 | 82.2s |
| #76 | Kimi K2.5 medium | Moonshot AI | 5 | 6.8 | 10/21 | 98.4s |