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: 失败次数 ↑.
| 排名 | 模型 | 公司 | 答案错误 次数 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #56 | MiMo-V2.5 medium | Xiaomi | 5 | 7.3 | 12/21 | 27.1s |
| #64 | MiMo-V2-Flash medium | Xiaomi | 5 | 7.2 | 12/21 | 20.1s |
| #72 | DeepSeek V3.2 medium | DeepSeek | 5 | 7.0 | 11/21 | 68.7s |
| #76 | Kimi K2.5 medium | Moonshot AI | 5 | 6.8 | 10/21 | 98.4s |
| #77 | Claude Sonnet 4.6 none | Anthropic | 5 | 6.8 | 11/21 | 5.04s |
| #80 | Mimo V2 Omni medium | Xiaomi | 5 | 6.7 | 10/21 | 41.2s |
| #96 | Ring-2.6-1T none | Inclusionai | 5 | 6.2 | 9/21 | 55.1s |
| #105 | Nemotron 3 Super medium | NVIDIA | 5 | 5.8 | 8/21 | 32.0s |
| #24 | GPT-5.2 Chat none | OpenAI | 6 | 7.9 | 14/21 | 7.13s |
| #28 | Gemini 2.5 Flash medium | 6 | 7.8 | 14/21 | 15.5s | |
| #31 | DeepSeek V4 Flash high | DeepSeek | 6 | 7.7 | 13/21 | 45.8s |
| #45 | GPT-5.4 Mini medium | OpenAI | 6 | 7.5 | 12/21 | 22.3s |
| #65 | Grok 4.20 medium | X AI | 6 | 7.1 | 12/21 | 27.7s |
| #71 | Step 3.7 Flash high | Stepfun | 6 | 7.0 | 11/21 | 64.5s |
| #75 | Ring-2.6-1T medium | Inclusionai | 6 | 6.9 | 11/21 | 61.3s |