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: 分数 ↑.
| 排名 | 模型 | 公司 | 答案错误 次数 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #133 | DeepSeek V3.2 none | DeepSeek | 7 | 5.2 | 6/21 | 13.8s |
| #132 | Mistral Small 4 medium | Mistral | 12 | 5.3 | 5/21 | 9.40s |
| #131 | Qwen3.5-122B-A10B none | Qwen | 13 | 5.3 | 6/21 | 3.41s |
| #130 | MiniMax M2.7 medium | Minimax | 6 | 5.3 | 5/21 | 38.2s |
| #129 | MiniMax M2.5 medium | Minimax | 7 | 5.3 | 5/21 | 65.4s |
| #128 | Qwen3.6 Flash none | Qwen | 12 | 5.4 | 7/21 | 1.60s |
| #127 | Grok 4.20 none | X AI | 10 | 5.4 | 6/18 | 1.11s |
| #126 | gpt-oss-120b none | OpenAI | 8 | 5.4 | 6/19 | 21.6s |
| #124 | Kimi K2.6 none | Moonshot AI | 11 | 5.5 | 7/21 | 13.3s |
| #125 | GPT-5.4 none | OpenAI | 13 | 5.5 | 7/21 | 1.42s |
| #123 | MiMo-V2.5-Pro none | Xiaomi | 11 | 5.5 | 6/21 | 1.78s |
| #121 | Owl Alpha none | Openrouter | 10 | 5.5 | 7/21 | 9.88s |
| #122 | GLM 4.7 Flash none | Z.ai | 13 | 5.5 | 6/21 | 2.86s |
| #120 | Mimo V2 PRO none | Xiaomi | 11 | 5.6 | 7/21 | 2.27s |
| #119 | Cobuddy medium | Baidu | 9 | 5.6 | 7/21 | 39.9s |