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) |
|---|---|---|---|---|---|---|
| #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 |
| #92 | Qwen3 Coder Next medium | Qwen | 10.0 | 4.7 | 1/1 | 2.64s |
| #66 | GPT-5.4 none | OpenAI | 10.0 | 5.9 | 1/1 | 2.75s |
| #55 | MiMo-V2-Omni none | Xiaomi | 10.0 | 6.5 | 1/1 | 2.76s |
| #85 | Elephant none | Openrouter | 3.0 | 5.2 | 0/1 | 2.79s |
| #81 | Elephant medium | Openrouter | 3.0 | 5.2 | 0/1 | 2.83s |
| #49 | Qwen3.5 Plus 2026-02-15 none | Qwen | 10.0 | 6.8 | 1/1 | 3.33s |
| #21 | Gemini 3 Flash Preview none | 10.0 | 8.1 | 1/1 | 3.35s | |
| #29 | Gemini 3.1 Flash Lite Preview none | 10.0 | 7.9 | 1/1 | 3.39s | |
| #96 | GPT-5.4 Nano none | OpenAI | 10.0 | 4.5 | 1/1 | 3.40s |
| #73 | Mistral Small 4 medium | Mistral | 10.0 | 5.7 | 1/1 | 3.50s |
| #67 | Qwen3.5-27B none | Qwen | 10.0 | 5.9 | 1/1 | 3.54s |
| #59 | Qwen3.5-Flash none | Qwen | 10.0 | 6.2 | 1/1 | 3.67s |
| #17 | Gemini 3.1 Flash Lite Preview medium | 10.0 | 8.2 | 1/1 | 3.80s |