CRMArena - PVI — leaderboard
Metric: PVI Score (%). Source: huggingface.co. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3 Sonnet | 41.5 |
| 2 | GPT-4o | 39.2 |
| 3 | Llama 3.1 70B | 37.7 |
| 4 | DeepSeek R1 | 34.6 |
| 5 | Llama 3.1 405B | 34.6 |
| 6 | Claude 3.5 Sonnet | 30 |
| 7 | O1 | 30 |
| 8 | GPT-4o Mini | 24.6 |
| 9 | Llama 3.1 8B | 15.4 |
Interactive version: theaggregate.ai/benchmark?slug=crmarena-pvi · How the rankings work · Data refreshed daily, snapshot 2026-07-22.