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: Response Time (avg) ↑.
| Rank | Model | Company | Tool Calling Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #12 | Gemini 3 PRO Preview medium | 10.0 | 8.4 | 1/1 | 12.0s | |
| #80 | MiniMax M2.7 medium | Minimax | 4.7 | 5.3 | 0/1 | 12.0s |
| #6 | Seed-2.0-Lite medium | Bytedance Seed | 10.0 | 8.6 | 1/1 | 12.4s |
| #25 | Grok 4.20 Beta medium | X AI | 3.0 | 8.0 | 0/1 | 12.4s |
| #31 | GLM 5V Turbo medium | Z.ai | 7.0 | 7.8 | 0/1 | 12.5s |
| #16 | GPT-5.4 medium | OpenAI | 10.0 | 8.2 | 1/1 | 13.3s |
| #47 | Grok 4.20 medium | X AI | 3.0 | 7.0 | 0/1 | 13.7s |
| #76 | Kimi K2.5 none | Moonshot AI | 10.0 | 5.5 | 1/1 | 14.0s |
| #71 | MiniMax M2.5 medium | Minimax | 10.0 | 5.7 | 1/1 | 15.4s |
| #13 | GLM 5 medium | Z.ai | 10.0 | 8.4 | 1/1 | 15.9s |
| #93 | GLM 4.7 Flash medium | Z.ai | 10.0 | 4.6 | 1/1 | 15.9s |
| #88 | Nemotron 3 Super none | NVIDIA | 4.7 | 5.1 | 0/1 | 16.0s |
| #50 | Hunter Alpha medium | OpenRouter | 10.0 | 6.7 | 1/1 | 17.3s |
| #45 | GPT-5 Mini medium | OpenAI | 10.0 | 7.0 | 1/1 | 18.6s |
| #2 | Gemini 3.1 Pro Preview medium | 10.0 | 9.6 | 1/1 | 23.1s |