CRMArena - NCR (Act): leaderboard
Metric: Exact match (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 7 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet (20240620) | 78.5 |
| 2 | Llama 3.1 405B Instruct | 46.2 |
| 3 | GPT-4o (2024-08-06) | 43.1 |
| 4 | Llama 3.1 70B Instruct | 28.5 |
| 5 | Claude 3 Sonnet (20240229) | 9.2 |
| 6 | GPT-4o Mini | 0.8 |
| 7 | Llama 3.1 8B Instruct | 0 |
Interactive version: theaggregate.ai/benchmark?slug=crmarena-ncr-act · How It Works · Data refreshed daily, snapshot 2026-10-09.