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。
311/311
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） |
|---|---|---|---|---|---|---|---|
| #1 | Gemini 3.6 Flash high | 10.0 | 9.9 | $0.699 | 1/1 | 8.35s | |
| #2 | Gemini 3.8 Flash high | 10.0 | 9.9 | $1.595 | 1/1 | 42.6s | |
| #3 | Gemini 3.7 Flash high | 10.0 | 9.8 | $0.646 | 1/1 | 16.3s | |
| #4 | Gemini 3.6 Flash medium | 10.0 | 9.8 | $0.427 | 1/1 | 5.78s | |
| #5 | GPT-5.6 Sol low | OpenAI | 10.0 | 9.5 | $0.357 | 1/1 | 7.56s |
| #6 | Gemini 3 Flash Preview medium | 10.0 | 9.5 | $0.763 | 1/1 | 12.6s | |
| #8 | Gemini 3.7 Flash medium | 10.0 | 9.4 | $0.309 | 1/1 | 5.83s | |
| #9 | GPT-5.6 Sol medium | OpenAI | 10.0 | 9.4 | $0.508 | 1/1 | 6.30s |
| #10 | GPT-5.6 Sol high | OpenAI | 10.0 | 9.4 | $0.446 | 1/1 | 7.08s |
| #11 | GPT-5.5 low | OpenAI | 10.0 | 9.3 | $1.257 | 1/1 | 4.96s |
| #12 | Grok 4.6 high | X AI | 10.0 | 9.3 | $1.908 | 1/1 | 13.3s |
| #13 | Gemini 3.1 Pro Preview medium | 10.0 | 9.2 | $1.352 | 1/1 | 23.1s | |
| #14 | Gemini 3.7 Flash low | 10.0 | 9.2 | $0.207 | 1/1 | 4.10s | |
| #15 | Claude Opus 5 high | Anthropic | 10.0 | 9.2 | $3.070 | 1/1 | 8.44s |
| #16 | Claude Opus 5 medium | Anthropic | 10.0 | 9.2 | $1.586 | 1/1 | 8.76s |