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: Tests Correct ↓.
| Rank | Model | Company | Tool Calling Score | Score | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|
| #71 | MiniMax M2.5 medium | Minimax | 10.0 | 5.7 | 1/1 | 15.4s |
| #72 | Hunter Alpha none | OpenRouter | 10.0 | 5.7 | 1/1 | 6.02s |
| #73 | Mistral Small 4 medium | Mistral | 10.0 | 5.7 | 1/1 | 3.50s |
| #75 | GLM 5.1 none | Z.ai | 10.0 | 5.6 | 1/1 | 10.7s |
| #76 | Kimi K2.5 none | Moonshot AI | 10.0 | 5.5 | 1/1 | 14.0s |
| #77 | GLM 5 Turbo none | Z.ai | 10.0 | 5.5 | 1/1 | 8.21s |
| #78 | Trinity Large Preview none | Arcee AI | 10.0 | 5.3 | 1/1 | 6.67s |
| #79 | Grok 4.20 Beta none | X AI | 10.0 | 5.3 | 1/1 | 4.79s |
| #82 | Grok 4.20 none | X AI | 10.0 | 5.2 | 1/1 | 4.63s |
| #83 | Mistral Small 4 none | Mistral | 10.0 | 5.2 | 1/1 | 1.40s |
| #87 | Qwen3 Coder Next none | Qwen | 10.0 | 5.1 | 1/1 | 2.47s |
| #89 | GPT-4o-mini none | OpenAI | 10.0 | 4.9 | 1/1 | 2.51s |
| #90 | Qwen3.5-9B none | Qwen | 10.0 | 4.8 | 1/1 | 1.27s |
| #91 | Mercury 2 none | Inception | 10.0 | 4.8 | 1/1 | 1.27s |
| #92 | Qwen3 Coder Next medium | Qwen | 10.0 | 4.7 | 1/1 | 2.64s |