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） |
|---|---|---|---|---|---|---|
| #9 | Qwen3.6 Plus Preview medium | Qwen | 3 | 8.5 | 13/17 | 13.9s |
| #40 | GPT-5.2 medium | OpenAI | 2 | 7.5 | 11/18 | 14.0s |
| #31 | GLM 5V Turbo medium | Z.ai | 3 | 7.8 | 11/18 | 15.0s |
| #44 | GPT-5.4 Mini medium | OpenAI | 4 | 7.3 | 9/18 | 15.2s |
| #20 | Qwen3.6 Plus medium | Qwen | 3 | 8.1 | 13/18 | 15.3s |
| #7 | GPT-5.3-Codex medium | OpenAI | 3 | 8.6 | 13/18 | 15.4s |
| #2 | Gemini 3.1 Pro Preview medium | 1 | 9.6 | 17/18 | 16.0s | |
| #68 | gpt-oss-120b medium | OpenAI | 7 | 5.8 | 7/18 | 16.1s |
| #35 | MiMo-V2-Omni medium | Xiaomi | 3 | 7.7 | 11/18 | 16.8s |
| #18 | GLM 5 Turbo medium | Z.ai | 3 | 8.1 | 12/18 | 17.7s |
| #16 | GPT-5.4 medium | OpenAI | 3 | 8.2 | 13/18 | 18.6s |
| #51 | Nemotron 3 Super medium | NVIDIA | 3 | 6.7 | 9/18 | 19.1s |
| #37 | Claude Opus 4.6 medium | Anthropic | 2 | 7.6 | 12/18 | 21.1s |
| #13 | GLM 5 medium | Z.ai | 2 | 8.4 | 13/18 | 23.3s |
| #41 | MiMo-V2-Flash medium | Xiaomi | 3 | 7.5 | 11/18 | 23.4s |