CRMArena - MTA — leaderboard
Metric: MTA Score (%). Source: huggingface.co. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Llama 3.1 405B | 86.9 |
| 2 | O1 | 84.6 |
| 3 | Llama 3.1 70B | 43.8 |
| 4 | GPT-4o | 29.2 |
| 5 | Claude 3.5 Sonnet | 26.9 |
| 6 | DeepSeek R1 | 13.8 |
| 7 | GPT-4o Mini | 6.2 |
| 8 | Claude 3 Sonnet | 1.5 |
| 9 | Llama 3.1 8B | 0 |
Interactive version: theaggregate.ai/benchmark?slug=crmarena-mta · How the rankings work · Data refreshed daily, snapshot 2026-07-22.