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) |
|---|---|---|---|---|---|---|---|
| #145 | Mercury 2 medium | Inception | 10.0 | 7.0 | $0.094 | 1/1 | 1.89s |
| #316 | Nemotron 3.5 Lightning none | NVIDIA | 2.8 | 4.0 | $0.007 | 0/1 | 1.70s |
| #277 | Mercury 2.5 Preview low | Inception | 2.8 | 5.0 | $0.011 | 0/1 | 1.57s |
| #302 | Laguna S 2.1 none | Poolside | 4.7 | 4.5 | $0.022 | 0/1 | 1.45s |
| #267 | Mistral Small 4 none | Mistral | 10.0 | 5.1 | $0.022 | 1/1 | 1.40s |
| #172 | Gemini 3.5 Flash Lite low | 10.0 | 6.6 | $0.138 | 1/1 | 1.39s | |
| #308 | Granite 4.2 8B none | IBM Granite | 10.0 | 4.3 | $0.037 | 1/1 | 1.39s |
| #258 | Laguna XS 2.1 none | Poolside | 10.0 | 5.3 | $0.008 | 1/1 | 1.36s |
| #282 | Mercury 2.5 Preview none | Inception | 10.0 | 4.9 | $0.018 | 1/1 | 1.29s |
| #273 | Qwen3.5-9B none | Qwen | 10.0 | 5.1 | $0.021 | 1/1 | 1.27s |
| #298 | Mercury 2 none | Inception | 10.0 | 4.7 | $0.030 | 1/1 | 1.27s |
| #318 | Mercury 2.5 none | Inception | 10.0 | 3.9 | $0.016 | 1/1 | 1.23s |
| #79 | Kimi K3 max | Moonshot AI | 3.0 | 7.9 | $2.528 | 0/1 | 0ms |
| #89 | Qwen3.8 27B medium | Qwen | 3.0 | 7.8 | ~$0.058 | 0/1 | 0ms |
| #115 | Kimi K2.7 Code medium | Moonshot AI | 3.0 | 7.4 | $0.655 | 0/1 | 0ms |