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) |
|---|---|---|---|---|---|---|
| #36 | GPT-5.3 Chat none | OpenAI | 10.0 | 7.7 | 1/1 | 8.36s |
| #34 | Kimi K2.6 medium | Moonshot AI | 10.0 | 7.7 | 1/1 | 8.92s |
| #24 | Gemma 4 26B A4B medium | 10.0 | 8.0 | 1/1 | 9.01s | |
| #22 | Gemini 3.1 Flash Lite Preview low | 10.0 | 8.1 | 1/1 | 9.54s | |
| #44 | GPT-5.4 Mini medium | OpenAI | 4.7 | 7.3 | 0/1 | 9.62s |
| #37 | Claude Opus 4.6 medium | Anthropic | 10.0 | 7.6 | 1/1 | 9.73s |
| #18 | GLM 5 Turbo medium | Z.ai | 10.0 | 8.1 | 1/1 | 9.84s |
| #40 | GPT-5.2 medium | OpenAI | 4.7 | 7.5 | 0/1 | 10.3s |
| #32 | Qwen3.5-Flash medium | Qwen | 10.0 | 7.8 | 1/1 | 10.3s |
| #1 | Gemini 3 Flash Preview medium | 10.0 | 10.0 | 1/1 | 10.6s | |
| #75 | GLM 5.1 none | Z.ai | 10.0 | 5.6 | 1/1 | 10.7s |
| #35 | MiMo-V2-Omni medium | Xiaomi | 10.0 | 7.7 | 1/1 | 11.1s |
| #53 | GLM 5 none | Z.ai | 10.0 | 6.6 | 1/1 | 11.1s |
| #64 | DeepSeek V3.2 none | DeepSeek | 10.0 | 6.1 | 1/1 | 11.8s |
| #30 | Step 3.5 Flash medium | Stepfun | 10.0 | 7.9 | 1/1 | 11.9s |