无效工具调用 失败
看看哪些 AI 模型最常遇到 无效工具调用，让你在选择前先发现稳定性风险。 排序方式: 总成本 ↑.
190/190
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 | 无效工具调用 次数 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #219 | Step 3.7 Flash high | Stepfun | 1 | 0.7 | $1.478 | 11/23 | 72.7s |
| #184 | Ember-1 low | Fireworks | 1 | 0.7 | $1.488 | 13/23 | 34.9s |
| #72 | Claude Sonnet 5.5 xhigh | Anthropic | 1 | 0.9 | $1.516 | 16/23 | 15.0s |
| #41 | Pareto default | Unbiased | 1 | 0.9 | $1.520 | 19/23 | 33.5s |
| #55 | Muse Spark 1.2 medium | Meta | 1 | 0.9 | $1.590 | 15/23 | 21.3s |
| #196 | Kimi K2.6 medium | Moonshot AI | 1 | 0.7 | $1.594 | 12/23 | 121.3s |
| #56 | Muse Spark 1.1 medium | Meta | 1 | 0.9 | $1.665 | 16/23 | 27.0s |
| #79 | Qwen3.7 Max medium | Qwen | 1 | 0.9 | $1.689 | 17/23 | 48.4s |
| #47 | Muse Spark 1.3 medium | Meta | 1 | 0.9 | $1.712 | 18/23 | 39.8s |
| #265 | Gemini 3.5 Flash none | 1 | 0.6 | $1.752 | 14/23 | 14.1s | |
| #58 | Pareto 26.9 default | Unbiased | 1 | 0.9 | $1.864 | 15/23 | 28.3s |
| #54 | Muse Spark 1.2 high | Meta | 1 | 0.9 | $2.018 | 15/23 | 28.1s |
| #191 | Ember-1 high | Fireworks | 1 | 0.7 | $2.405 | 12/23 | 58.1s |
| #87 | Muse Spark 1.1 high | Meta | 2 | 0.8 | $2.570 | 13/23 | 37.4s |
| #92 | Gemini 3.5 Flash high | 2 | 0.8 | $2.737 | 19/23 | 18.6s |