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） |
|---|---|---|---|---|---|---|
| #39 | Qwen3.6 Flash medium | Qwen | 8 | 7.5 | 12/21 | 19.2s |
| #1 | Gemini 3 Flash Preview medium | 1 | 9.8 | 20/21 | 18.6s | |
| #46 | Qwen3.6 35B A3B medium | Qwen | 4 | 7.4 | 13/21 | 18.1s |
| #149 | Nemotron 3 Nano Omni 30b A3b Reasoning medium | NVIDIA | 7 | 4.6 | 4/19 | 17.1s |
| #52 | Claude Sonnet 4.6 medium | Anthropic | 4 | 7.4 | 13/21 | 17.1s |
| #42 | GPT-5.2 medium | OpenAI | 3 | 7.5 | 13/21 | 16.9s |
| #33 | Hy3 preview medium | Tencent | 3 | 7.7 | 14/21 | 16.3s |
| #15 | GPT-5.3-Codex medium | OpenAI | 4 | 8.4 | 15/21 | 16.2s |
| #5 | Qwen3.7 Max medium | Qwen | 3 | 9.1 | 18/21 | 16.0s |
| #57 | Step 3.7 Flash low | Stepfun | 8 | 7.3 | 12/21 | 15.7s |
| #28 | Gemini 2.5 Flash medium | 6 | 7.8 | 14/21 | 15.5s | |
| #93 | Qwen3.6 Plus Preview medium | Qwen | 2 | 6.3 | 9/19 | 15.2s |
| #41 | Nemotron 3 Ultra 550b A55b medium | NVIDIA | 7 | 7.5 | 13/21 | 15.1s |
| #92 | Laguna M.1 medium | Poolside | 4 | 6.4 | 9/19 | 14.7s |
| #133 | DeepSeek V3.2 none | DeepSeek | 7 | 5.2 | 6/21 | 13.8s |