CRMArena - KQA — leaderboard
Metric: KQA Score (%). Source: huggingface.co. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek R1 | 61.2 |
| 2 | O1 | 58.8 |
| 3 | Llama 3.1 405B | 55.3 |
| 4 | GPT-4o Mini | 52.8 |
| 5 | GPT-4o | 50.2 |
| 6 | Llama 3.1 70B | 48.7 |
| 7 | Claude 3.5 Sonnet | 45 |
| 8 | Claude 3 Sonnet | 23.2 |
| 9 | Llama 3.1 8B | 4 |
Interactive version: theaggregate.ai/benchmark?slug=crmarena-kqa · How the rankings work · Data refreshed daily, snapshot 2026-07-22.