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: 总成本 ↑.
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 | 工具调用 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #100 | Hy3 preview medium | Tencent | 10.0 | 6.5 | $0.018 | 1/1 | 15.0s |
| #121 | gpt-oss-120b medium | OpenAI | 9.8 | 6.1 | $0.019 | 1/1 | 6.91s |
| #209 | Step 3.5 Flash none | Stepfun | 3.0 | 2.3 | $0.020 | 0/1 | 0ms |
| #169 | Qwen3.5-9B none | Qwen | 10.0 | 5.1 | $0.021 | 1/1 | 1.27s |
| #157 | Mimo V2 Omni none | Xiaomi | 10.0 | 5.5 | $0.021 | 1/1 | 5.40s |
| #165 | Mistral Small 4 none | Mistral | 10.0 | 5.1 | $0.022 | 1/1 | 1.40s |
| #166 | Qwen3 Coder Next none | Qwen | 10.0 | 5.1 | $0.025 | 1/1 | 2.47s |
| #200 | MiMo-V2-Flash none | Xiaomi | 10.0 | 4.0 | $0.025 | 1/1 | 2.28s |
| #168 | MiMo-V2.5 none | Xiaomi | 10.0 | 5.1 | $0.025 | 1/1 | 2.43s |
| #179 | Ring-2.6-1T none | Inclusionai | 3.0 | 4.8 | $0.026 | 0/1 | 0ms |
| #189 | Mercury 2 none | Inception | 10.0 | 4.6 | $0.030 | 1/1 | 1.27s |
| #187 | Qwen3 Coder Next medium | Qwen | 10.0 | 4.7 | $0.032 | 1/1 | 2.64s |
| #186 | Laguna M.1 medium | Poolside | 10.0 | 4.7 | $0.033 | 1/1 | 6.31s |
| #115 | Gemma 4 31B none | 3.0 | 6.2 | $0.035 | 0/1 | 0ms | |
| #204 | Qwen3.5-9B medium | Qwen | 10.0 | 3.8 | $0.036 | 1/1 | 4.31s |