AI BENCHY 分类
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 ↑.
| 排名 | 模型 | 公司 | 工具调用 得分 | 分数 | 测试正确 | 响应时间（平均） |
|---|---|---|---|---|---|---|
| #160 | LFM2-24B-A2B none | Liquid | 3.0 | 4.2 | 0/1 | 0ms |
| #162 | Nemotron 3 Nano Omni 30b A3b Reasoning none | NVIDIA | 3.0 | 4.1 | 0/1 | 0ms |
| #1 | Gemini 3 Flash Preview medium | 10.0 | 9.8 | 1/1 | 12.6s | |
| #2 | Gemini 3.5 Flash high | 9.8 | 9.6 | 1/1 | 4.96s | |
| #3 | Gemini 3.5 Flash low | 10.0 | 9.4 | 1/1 | 3.27s | |
| #4 | Gemini 3.1 Pro Preview medium | 10.0 | 9.4 | 1/1 | 23.1s | |
| #5 | Qwen3.7 Max medium | Qwen | 10.0 | 9.1 | 1/1 | 6.63s |
| #6 | GPT-5.5 low | OpenAI | 10.0 | 9.0 | 1/1 | 4.96s |
| #7 | Gemini 3.5 Flash medium | 10.0 | 9.0 | 1/1 | 3.81s | |
| #8 | Claude Opus 4.7 none | Anthropic | 10.0 | 8.9 | 1/1 | 4.74s |
| #9 | GPT-5.5 medium | OpenAI | 10.0 | 8.8 | 1/1 | 10.6s |
| #10 | Claude Opus 4.8 medium | Anthropic | 10.0 | 8.7 | 1/1 | 8.96s |
| #11 | Claude Opus 4.7 medium | Anthropic | 10.0 | 8.7 | 1/1 | 4.17s |
| #12 | Gemini 3.1 Flash Lite Preview high | 10.0 | 8.6 | 1/1 | 7.73s | |
| #14 | Qwen3.6 Max Preview medium | Qwen | 10.0 | 8.5 | 1/1 | 18.3s |