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) |
|---|---|---|---|---|---|---|
| #14 | Gemma 4 31B medium | 3.0 | 8.3 | 0/1 | 0ms | |
| #33 | GLM 5.1 medium | Z.ai | 3.0 | 7.8 | 0/1 | 0ms |
| #48 | Gemma 4 31B none | 3.0 | 6.9 | 0/1 | 0ms | |
| #56 | Grok 4.20 Multi Agent Beta medium | X AI | 3.0 | 6.4 | 0/1 | 0ms |
| #84 | gpt-oss-120b none | OpenAI | 3.0 | 5.2 | 0/1 | 0ms |
| #98 | LFM2-24B-A2B none | Liquid | 3.0 | 4.1 | 0/1 | 0ms |
| #91 | Mercury 2 none | Inception | 10.0 | 4.8 | 1/1 | 1.27s |
| #90 | Qwen3.5-9B none | Qwen | 10.0 | 4.8 | 1/1 | 1.27s |
| #83 | Mistral Small 4 none | Mistral | 10.0 | 5.2 | 1/1 | 1.40s |
| #54 | Mercury 2 medium | Inception | 10.0 | 6.5 | 1/1 | 1.89s |
| #62 | Gemini 2.5 Flash none | 10.0 | 6.2 | 1/1 | 1.91s | |
| #70 | Qwen3.5-122B-A10B none | Qwen | 10.0 | 5.7 | 1/1 | 2.04s |
| #94 | MiMo-V2-Flash none | Xiaomi | 10.0 | 4.5 | 1/1 | 2.28s |
| #63 | Qwen3.5-35B-A3B none | Qwen | 10.0 | 6.1 | 1/1 | 2.30s |
| #86 | GPT-5.4 Mini none | OpenAI | 3.0 | 5.1 | 0/1 | 2.32s |