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 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #46 | Gemini 3.5 Flash low | 1.0 | 0.9 | $0.752 | 1/1 | 3.27s | |
| #12 | GPT-6.1 Sol high | OpenAI | 1.0 | 1.0 | $0.755 | 1/1 | 7.83s |
| #100 | DeepSeek V4.1 Flash 1017 max | DeepSeek | 1.0 | 0.8 | $0.757 | 1/1 | 2.43s |
| #174 | LongCat 2.0 medium | Meituan | 1.0 | 0.7 | $0.767 | 1/1 | 10.7s |
| #113 | Gemini 3.8 Flash medium | 1.0 | 0.8 | $0.769 | 1/1 | 18.5s | |
| #165 | LongCat 2.0 high | Meituan | 1.0 | 0.7 | $0.778 | 1/1 | 10.0s |
| #191 | Grok 4.6 low | X AI | 1.0 | 0.7 | $0.781 | 1/1 | 14.4s |
| #152 | Qwen3.6 Flash medium | Qwen | 1.0 | 0.7 | $0.783 | 1/1 | 4.00s |
| #329 | Ember-1 none | Fireworks | 0.3 | 0.5 | $0.786 | 0/1 | 26.4s |
| #301 | Trinity Large Thinking high | Arcee AI | 1.0 | 0.6 | $0.794 | 1/1 | 5.96s |
| #216 | GPT-5.6 Sol none | OpenAI | 1.0 | 0.7 | $0.795 | 1/1 | 3.70s |
| #240 | Beam 1.0 501B A23B max | Reflection | 0.3 | 0.6 | $0.799 | 0/1 | 2.15s |
| #229 | Qwen3.6 35B A3B medium | Qwen | 0.3 | 0.7 | $0.834 | 0/1 | 0ms |
| #244 | Kimi K2.5 medium | Moonshot AI | 1.0 | 0.6 | $0.841 | 1/1 | 31.7s |
| #275 | Trinity Large Thinking medium | Arcee AI | 1.0 | 0.6 | $0.862 | 1/1 | 5.26s |