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) ↑.
330/330
Filter models
No models match the current search and filters.
| Rank | Model | Company | Tool Calling Score | Score | Total Cost | Tests Correct | Response Time (avg) |
|---|---|---|---|---|---|---|---|
| #99 | GPT-5.6 Luna high | OpenAI | 10.0 | 7.6 | $0.179 | 1/1 | 4.98s |
| #120 | Gemini 3 Flash Preview low | 10.0 | 7.4 | $0.185 | 1/1 | 4.99s | |
| #136 | Muse Glimmer 30B low | Meta | 10.0 | 7.1 | $0.143 | 1/1 | 5.04s |
| #287 | Nemotron 3.5 Lightning low | NVIDIA | 10.0 | 4.8 | $0.140 | 1/1 | 5.08s |
| #87 | GPT-5.6 Terra medium | OpenAI | 10.0 | 7.8 | $0.523 | 1/1 | 5.09s |
| #291 | KAT-Coder-Air V2.5 none | Kwaipilot | 10.0 | 4.8 | $0.070 | 1/1 | 5.13s |
| #209 | Trinity Large Thinking low | Arcee AI | 10.0 | 6.0 | $0.625 | 1/1 | 5.19s |
| #31 | Qwen3.8 Max (0902) high | Qwen | 10.0 | 8.9 | $2.736 | 1/1 | 5.21s |
| #204 | Trinity Large Thinking medium | Arcee AI | 10.0 | 6.1 | $0.756 | 1/1 | 5.26s |
| #184 | Qwen3.6 Max Preview none | Qwen | 10.0 | 6.4 | $0.228 | 1/1 | 5.27s |
| #128 | Claude Opus 4.8 none | Anthropic | 10.0 | 7.3 | $1.166 | 1/1 | 5.35s |
| #247 | Mimo V2 Omni none | Xiaomi | 10.0 | 5.5 | $0.021 | 1/1 | 5.40s |
| #75 | DeepSeek V4 Flash 0731 high | DeepSeek | 10.0 | 8.0 | $0.058 | 1/1 | 5.42s |
| #321 | Grok 4.1 Fast none | X AI | 2.8 | 3.8 | $0.008 | 0/1 | 5.51s |
| #112 | Gemini 3.8 Flash low | 10.0 | 7.5 | $0.239 | 1/1 | 5.51s |