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: 分数 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #92 | Gemini 3.5 Flash high | 2 | 0.8 | $2.737 | 19/23 | 18.6s | |
| #90 | GPT-5.6 Terra high | OpenAI | 1 | 0.8 | $0.698 | 15/23 | 13.6s |
| #87 | Muse Spark 1.1 high | Meta | 2 | 0.8 | $2.570 | 13/23 | 37.4s |
| #86 | Inkling high | Thinkingmachines | 2 | 0.8 | $1.238 | 16/23 | 62.7s |
| #84 | Muse Glimmer 30B xhigh | Meta | 1 | 0.8 | $0.585 | 14/23 | 97.7s |
| #82 | Qwen3.8 2.4T A95B low | Qwen | 1 | 0.8 | $4.016 | 16/23 | 120.4s |
| #79 | Qwen3.7 Max medium | Qwen | 1 | 0.9 | $1.689 | 17/23 | 48.4s |
| #78 | Claude Sonnet 5 medium | Anthropic | 1 | 0.9 | $1.438 | 16/23 | 15.0s |
| #77 | Muse Spark 1.3 low | Meta | 1 | 0.9 | $0.911 | 16/23 | 17.7s |
| #75 | Qwen3.8 Max (0902) low | Qwen | 1 | 0.9 | $1.131 | 18/23 | 29.1s |
| #73 | Claude Sonnet 5.5 high | Anthropic | 1 | 0.9 | $1.175 | 16/23 | 10.8s |
| #71 | Muse Spark 1.1 low | Meta | 1 | 0.9 | $0.885 | 14/23 | 13.2s |
| #72 | Claude Sonnet 5.5 xhigh | Anthropic | 1 | 0.9 | $1.516 | 16/23 | 15.0s |
| #58 | Pareto 26.9 default | Unbiased | 1 | 0.9 | $1.864 | 15/23 | 28.3s |
| #57 | Claude Fable 5 medium | Anthropic | 1 | 0.9 | $5.089 | 18/23 | 16.8s |