工具调用 排名
看看哪些 AI 模型在 工具调用 上表现最好，哪些更稳定，以及差距主要出现在哪里。 排序方式: 测试正确 ↓.
451/451
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 | 工具调用 得分 | 分数 | 总成本 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|---|
| #129 | Step 3.7 Flash medium | Stepfun | 1.0 | 0.8 | $0.571 | 1/1 | 4.16s |
| #130 | Grok 4.6 medium | X AI | 1.0 | 0.8 | $2.270 | 1/1 | 12.8s |
| #131 | Qwen3.7 Plus none | Qwen | 1.0 | 0.8 | $0.178 | 1/1 | 3.54s |
| #132 | Grok 4.5 low | X AI | 1.0 | 0.8 | $1.345 | 1/1 | 5.83s |
| #133 | DeepSeek V4 Flash 0731 medium | DeepSeek | 1.0 | 0.8 | $0.460 | 1/1 | 4.41s |
| #134 | Muse Wonder high | Meta | 1.0 | 0.8 | $3.426 | 1/1 | 23.7s |
| #135 | GPT-6 Luna high | OpenAI | 1.0 | 0.8 | $0.074 | 1/1 | 6.96s |
| #136 | Muse Glimmer 30B high | Meta | 1.0 | 0.8 | $0.506 | 1/1 | 6.41s |
| #137 | Nemotron 3.5 Super VL medium | NVIDIA | 1.0 | 0.8 | $0.437 | 1/1 | 36.3s |
| #138 | Claude Haiku 5.5 medium | Anthropic | 1.0 | 0.8 | $0.063 | 1/1 | 5.02s |
| #139 | Qwen3.5 Plus 2026-04-20 medium | Qwen | 1.0 | 0.8 | $0.435 | 1/1 | 14.7s |
| #140 | Qwen3.7 Flash low | Qwen | 1.0 | 0.8 | $0.071 | 1/1 | 7.66s |
| #141 | Muse Glimmer 30B medium | Meta | 1.0 | 0.8 | $0.288 | 1/1 | 5.64s |
| #142 | Muse Wonder xhigh | Meta | 1.0 | 0.8 | $4.012 | 1/1 | 28.0s |
| #143 | Qwen3.8 Flash Next medium | Qwen | 1.0 | 0.8 | ~$0.047 | 1/1 | 5.75s |