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） |
|---|---|---|---|---|---|---|---|
| #314 | Nemotron 3.5 Super VL none | NVIDIA | 1.0 | 0.6 | $0.040 | 1/1 | 34.0s |
| #40 | Muse Spark 1.3 high | Meta | 1.0 | 0.9 | $1.891 | 1/1 | 33.9s |
| #419 | Hy3 preview none | Tencent | 1.0 | 0.3 | $0.007 | 1/1 | 33.8s |
| #302 | GPT-5 Nano medium | OpenAI | 1.0 | 0.6 | $0.159 | 1/1 | 33.3s |
| #122 | Qwen3.8 2.4T A95B high | Qwen | 1.0 | 0.8 | $2.949 | 1/1 | 32.9s |
| #244 | Kimi K2.5 medium | Moonshot AI | 1.0 | 0.6 | $0.841 | 1/1 | 31.7s |
| #17 | Gemini 4 Argon high | 1.0 | 1.0 | $1.802 | 1/1 | 28.5s | |
| #48 | Muse Spark 1.3 medium | Meta | 1.0 | 0.9 | $1.712 | 1/1 | 28.3s |
| #235 | KAT-Coder-Pro V2.5 high | Kwaipilot | 1.0 | 0.6 | $0.506 | 1/1 | 28.0s |
| #142 | Muse Wonder xhigh | Meta | 1.0 | 0.8 | $4.012 | 1/1 | 28.0s |
| #342 | MiMo-V2-Flash medium | Xiaomi | 1.0 | 0.5 | $0.043 | 1/1 | 27.8s |
| #402 | Grok 4.1 Fast medium | X AI | 0.3 | 0.4 | $0.069 | 0/1 | 27.7s |
| #69 | Seed 2.1 Turbo medium | Bytedance Seed | 1.0 | 0.9 | $2.042 | 1/1 | 27.5s |
| #29 | Seed 2.1 Turbo low | Bytedance Seed | 1.0 | 0.9 | $1.645 | 1/1 | 27.4s |
| #196 | Ember-1 high | Fireworks | 0.3 | 0.7 | $2.405 | 0/1 | 26.5s |