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） |
|---|---|---|---|---|---|---|---|
| #166 | Qwen3.5 Plus 2026-02-15 medium | Qwen | 1 | 0.7 | $0.567 | 14/23 | 97.7s |
| #156 | Inkling medium | Thinkingmachines | 2 | 0.7 | $0.527 | 15/23 | 17.0s |
| #240 | Gemini 3.5 Flash minimal | 2 | 0.6 | $0.508 | 13/23 | 4.67s | |
| #229 | KAT-Coder-Pro V2.5 high | Kwaipilot | 1 | 0.6 | $0.506 | 11/23 | 21.2s |
| #130 | DeepSeek V4 Flash 0731 medium | DeepSeek | 1 | 0.8 | $0.460 | 12/23 | 94.2s |
| #312 | GLM 5V Turbo medium | Z.ai | 2 | 0.5 | $0.457 | 11/21 | 23.1s |
| #228 | GLM 5.1 none | Z.ai | 1 | 0.6 | $0.451 | 9/23 | 11.1s |
| #173 | Step 3.7 Flash low | Stepfun | 2 | 0.7 | $0.449 | 11/23 | 20.7s |
| #164 | Gemini 3.5 Flash Lite medium | 2 | 0.7 | $0.440 | 14/23 | 8.68s | |
| #384 | MiniMax M2.5 medium | Minimax | 1 | 0.4 | $0.440 | 5/23 | 102.3s |
| #113 | GPT-5.6 Terra low | OpenAI | 1 | 0.8 | $0.435 | 14/23 | 7.58s |
| #238 | Beam 1.0 501B A23B low | Reflection | 1 | 0.6 | $0.432 | 11/23 | 4.89s |
| #97 | Qwen3.7 Plus medium | Qwen | 1 | 0.8 | $0.415 | 16/23 | 59.7s |
| #289 | DeepSeek V4.1 Flash none | DeepSeek | 1 | 0.6 | $0.391 | 7/23 | 16.6s |
| #288 | GPT-5.6 Terra none | OpenAI | 1 | 0.6 | $0.377 | 8/23 | 4.11s |