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。
83/83
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） |
|---|---|---|---|---|---|---|---|
| #174 | Ling-2.6-flash none | Inclusionai | 3 | 4.9 | $0.002 | 6/22 | 10.7s |
| #27 | Muse Spark 1.1 high | Meta | 2 | 8.1 | $1.694 | 12/22 | 31.5s |
| #28 | Inkling high | Thinkingmachines | 2 | 8.0 | $1.006 | 15/22 | 64.2s |
| #87 | Gemini 3.5 Flash minimal | 2 | 6.8 | $0.300 | 14/22 | 2.65s | |
| #91 | GLM 5V Turbo medium | Z.ai | 2 | 6.7 | $0.457 | 11/21 | 23.1s |
| #96 | Qwen3.6 27B medium | Qwen | 2 | 6.5 | $0.779 | 10/22 | 106.3s |
| #119 | Inkling low | Thinkingmachines | 2 | 6.1 | $0.187 | 10/22 | 5.15s |
| #120 | Qwen3.6 Flash none | Qwen | 2 | 6.1 | $0.062 | 7/22 | 3.74s |
| #146 | DeepSeek V4 Flash none | DeepSeek | 2 | 5.6 | $0.044 | 5/22 | 36.8s |
| #148 | Qwen3.6 27B none | Qwen | 2 | 5.5 | $0.087 | 7/22 | 10.7s |
| #165 | Qwen3.5-9B none | Qwen | 2 | 5.1 | $0.021 | 4/22 | 19.2s |
| #167 | North Mini Code none | Cohere | 2 | 5.1 | $0.000 | 4/22 | 29.9s |
| #169 | DeepSeek V3.2 none | DeepSeek | 2 | 5.0 | $0.054 | 6/22 | 18.3s |
| #172 | GLM 4.7 Flash none | Z.ai | 2 | 4.9 | $0.016 | 6/22 | 9.15s |
| #190 | GLM 4.7 Flash medium | Z.ai | 2 | 4.3 | $0.166 | 4/22 | 142.6s |