CRMArena - TCU (Function Calling Native): leaderboard
Metric: Exact match (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 4 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 82.3 |
| 2 | GPT-4o (2024-08-06) | 81.5 |
| 3 | Claude 3 Sonnet (20240229) | 30 |
| 4 | GPT-4o Mini | 10.8 |
Interactive version: theaggregate.ai/benchmark?slug=crmarena-tcu-function-calling-native · How It Works · Data refreshed daily, snapshot 2026-10-09.