CRMArena - TCU — leaderboard
Metric: TCU Score (%). Source: huggingface.co. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Claude 3.5 Sonnet | 82.3 |
| 2 | GPT-4o | 81.5 |
| 3 | O1 | 66.9 |
| 4 | Llama 3.1 405B | 64.6 |
| 5 | Llama 3.1 70B | 44.6 |
| 6 | DeepSeek R1 | 30.1 |
| 7 | Claude 3 Sonnet | 30 |
| 8 | GPT-4o Mini | 25.4 |
| 9 | Llama 3.1 8B | 1.5 |
Interactive version: theaggregate.ai/benchmark?slug=crmarena-tcu · How the rankings work · Data refreshed daily, snapshot 2026-07-22.