领域专项 排名
看看哪些 AI 模型在 领域专项 上表现最好，哪些更稳定，以及差距主要出现在哪里。 排序方式: 测试正确 ↓.
210/210
筛选模型
没有模型匹配当前搜索和筛选条件。
| 排名 | 模型 | 公司 | 领域专项 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #1 | Gemini 3 Flash Preview medium | 10.0 | 9.6 | $0.742 | 3/3 | 15.3s | |
| #88 | Gemini 3.5 Flash minimal | 10.0 | 6.8 | $0.300 | 3/3 | 899ms | |
| #209 | Step 3.5 Flash none | Stepfun | 3.3 | 2.3 | $0.020 | 1/1 | 34.5s |
| #2 | Gemini 3.5 Flash high | 7.6 | 9.5 | $1.976 | 2/3 | 14.1s | |
| #7 | Gemini 3.1 Pro Preview medium | 7.7 | 9.2 | $1.361 | 2/3 | 32.7s | |
| #9 | Gemini 3.5 Flash medium | 7.7 | 9.1 | $0.642 | 2/3 | 5.24s | |
| #11 | Gemini 3.5 Flash low | 7.7 | 8.9 | $0.433 | 2/3 | 3.39s | |
| #15 | Claude Opus 4.7 medium | Anthropic | 7.7 | 8.7 | $1.477 | 2/3 | 1.17s |
| #23 | Claude Sonnet 5 medium | Anthropic | 7.7 | 8.3 | $0.922 | 2/3 | 20.4s |
| #28 | Inkling high | Thinkingmachines | 7.7 | 8.0 | $1.006 | 2/3 | 186.4s |
| #29 | Step 3.7 Flash medium | Stepfun | 7.7 | 8.0 | $0.515 | 2/3 | 48.3s |
| #44 | GPT-5.6 Luna high | OpenAI | 7.7 | 7.7 | $1.017 | 2/3 | 79.0s |
| #59 | Qwen3.7 Max none | Qwen | 7.7 | 7.4 | $0.197 | 2/3 | 975ms |
| #63 | Claude Sonnet 4.6 none | Anthropic | 7.7 | 7.3 | $0.661 | 2/3 | 3.54s |
| #79 | Gemini 3.5 Flash none | 7.6 | 7.0 | $1.079 | 2/3 | 10.6s |