AI BENCHY Category
Tool Calling Ranking
See which AI models perform best on Tool Calling, which ones stay reliable, and where the biggest gaps appear. Sort by: Metric ↑.
| Rank | Model | Company | Tool Calling Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #143 | MiMo-V2.5 none | Xiaomi | 10.0 | 4.9 | 1/1 | 2.43s |
| #145 | Laguna M.1 none | Poolside | 10.0 | 4.8 | 1/1 | 7.54s |
| #147 | GPT-4o-mini none | OpenAI | 10.0 | 4.8 | 1/1 | 2.51s |
| #148 | GPT-5.4 Nano none | OpenAI | 10.0 | 4.7 | 1/1 | 3.40s |
| #150 | Qwen3 Coder Next medium | Qwen | 10.0 | 4.6 | 1/1 | 2.64s |
| #151 | Trinity Large Preview none | Arcee AI | 10.0 | 4.6 | 1/1 | 6.67s |
| #152 | MiMo-V2-Flash none | Xiaomi | 10.0 | 4.6 | 1/1 | 2.28s |
| #154 | Qwen3.5-9B none | Qwen | 10.0 | 4.6 | 1/1 | 1.27s |
| #155 | Mercury 2 none | Inception | 10.0 | 4.5 | 1/1 | 1.27s |
| #156 | Hy3 preview none | Tencent | 10.0 | 4.4 | 1/1 | 33.8s |
| #158 | GLM 4.7 Flash medium | Z.ai | 10.0 | 4.4 | 1/1 | 15.9s |
| #161 | Qwen3.5-9B medium | Qwen | 10.0 | 4.2 | 1/1 | 4.31s |
| #163 | Granite 4.1 8B none | IBM Granite | 10.0 | 4.0 | 1/1 | 2.17s |