工具调用 排名
看看哪些 AI 模型在 工具调用 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: 响应时间(平均) ↑.
451/451
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 | 工具调用 得分 | 分数 | 总成本 | 测试正确 | 响应时间(平均) |
|---|---|---|---|---|---|---|---|
| #370 | Laguna S 2.1 none | Poolside | 0.5 | 0.5 | $0.044 | 0/1 | 1.45s |
| #350 | Mercury 2.5 Preview low | Inception | 0.3 | 0.5 | $0.015 | 0/1 | 1.57s |
| #296 | DeepSeek V4.1 Flash 1017 none | DeepSeek | 1.0 | 0.6 | $0.055 | 1/1 | 1.60s |
| #327 | MiMo-V2.6-Flash none | Xiaomi | 1.0 | 0.5 | $0.060 | 1/1 | 1.65s |
| #406 | Nemotron 3.5 Lightning none | NVIDIA | 0.3 | 0.4 | $0.009 | 0/1 | 1.70s |
| #274 | Beam 1.0 501B A23B high | Reflection | 0.3 | 0.6 | $0.674 | 0/1 | 1.82s |
| #245 | Beam 1.0 501B A23B low | Reflection | 0.3 | 0.6 | $0.432 | 0/1 | 1.83s |
| #232 | Beam 1.0 501B A23B xhigh | Reflection | 0.3 | 0.6 | $0.688 | 0/1 | 1.84s |
| #223 | Mercury 2 medium | Inception | 1.0 | 0.7 | $0.121 | 1/1 | 1.89s |
| #318 | Gemini 2.5 Flash none | 1.0 | 0.5 | $0.017 | 1/1 | 1.91s | |
| #36 | DeepSeek V4.1 Flash 1017 low | DeepSeek | 1.0 | 0.9 | $0.355 | 1/1 | 1.92s |
| #425 | Laguna Xs.2 default | Poolside | 0.3 | 0.3 | $0.004 | 0/1 | 1.93s |
| #225 | Beam 1.0 501B A23B medium | Reflection | 0.3 | 0.7 | $0.499 | 0/1 | 1.95s |
| #238 | Qwen3.5-122B-A10B none | Qwen | 1.0 | 0.6 | $0.308 | 1/1 | 2.04s |
| #286 | Inkling Small medium | Thinkingmachines | 0.3 | 0.6 | $0.113 | 0/1 | 2.12s |