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: 测试正确 ↑.
216/216
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） |
|---|---|---|---|---|---|---|---|
| #92 | Gemini 3.5 Flash minimal | 10.0 | 6.8 | $0.300 | 1/1 | 2.79s | |
| #93 | Gemini 3 Flash Preview none | 10.0 | 6.8 | $0.085 | 1/1 | 3.35s | |
| #95 | Gemini 3.5 Flash-Lite low | 9.8 | 6.7 | $0.145 | 1/1 | 1.76s | |
| #96 | LongCat 2.0 low | Meituan | 10.0 | 6.7 | $0.391 | 1/1 | 10.8s |
| #97 | KAT-Coder-Pro V2.5 none | Kwaipilot | 10.0 | 6.7 | $0.476 | 1/1 | 5.93s |
| #99 | Claude Opus 4.7 none | Anthropic | 10.0 | 6.6 | $0.505 | 1/1 | 4.74s |
| #100 | Gemma 4 26B A4B medium | 10.0 | 6.6 | $0.089 | 1/1 | 9.01s | |
| #101 | GLM 5.2 none | Z.ai | 10.0 | 6.6 | $0.128 | 1/1 | 15.8s |
| #102 | LongCat 2.0 high | Meituan | 10.0 | 6.6 | $0.469 | 1/1 | 10.0s |
| #103 | Qwen3.6 Max Preview none | Qwen | 10.0 | 6.6 | $0.231 | 1/1 | 5.27s |
| #104 | Gemini 3.5 Flash-Lite medium | 10.0 | 6.5 | $0.369 | 1/1 | 2.63s | |
| #105 | Qwen3.6 27B medium | Qwen | 10.0 | 6.5 | $0.779 | 1/1 | 16.9s |
| #106 | Hy3 preview medium | Tencent | 10.0 | 6.5 | $0.018 | 1/1 | 15.0s |
| #107 | MiMo-V2.5 medium | Xiaomi | 10.0 | 6.5 | $0.082 | 1/1 | 7.29s |
| #108 | Laguna XS 2.1 medium | Poolside | 10.0 | 6.5 | $0.068 | 1/1 | 3.01s |