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: 测试正确 ↑.
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） |
|---|---|---|---|---|---|---|---|
| #186 | Qwen3.5-122B-A10B medium | Qwen | 2 | 0.7 | $1.152 | 14/23 | 67.0s |
| #192 | Gemma 4 31B medium | 1 | 0.7 | $0.144 | 14/23 | 78.8s | |
| #203 | Grok 4.7 xhigh | X AI | 1 | 0.7 | $3.398 | 14/23 | 124.0s |
| #248 | Gemini 3.1 Flash Lite Preview low | 1 | 0.6 | $0.736 | 14/23 | 19.0s | |
| #265 | Gemini 3.5 Flash none | 1 | 0.6 | $1.752 | 14/23 | 14.1s | |
| #54 | Muse Spark 1.2 high | Meta | 1 | 0.9 | $2.018 | 15/23 | 28.1s |
| #55 | Muse Spark 1.2 medium | Meta | 1 | 0.9 | $1.590 | 15/23 | 21.3s |
| #58 | Pareto 26.9 default | Unbiased | 1 | 0.9 | $1.864 | 15/23 | 28.3s |
| #90 | GPT-5.6 Terra high | OpenAI | 1 | 0.8 | $0.698 | 15/23 | 13.6s |
| #96 | Ling 3.1 Flash medium | Inclusionai | 1 | 0.8 | $0.000 | 15/23 | 88.7s |
| #112 | Qwen3.8 Flash Next low | Qwen | 1 | 0.8 | ~$0.045 | 15/23 | 23.7s |
| #115 | GLM 5.3 FlashX max | Z.ai | 2 | 0.8 | $0.623 | 15/23 | 44.0s |
| #120 | Qwen3.8 2.4T A95B high | Qwen | 1 | 0.8 | $2.949 | 15/23 | 120.9s |
| #123 | Ling 3.1 Flash high | Inclusionai | 1 | 0.8 | $0.000 | 15/23 | 87.4s |
| #132 | GPT-6 Luna high | OpenAI | 1 | 0.8 | $0.074 | 15/23 | 20.4s |