CRMArena - HTU (ReAct): leaderboard
Metric: Exact match (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | O1 (2024-12-17) | 51.5 |
| 2 | GPT-4o (2024-08-06) | 39.2 |
| 3 | GPT-4o Mini | 36.9 |
| 4 | Claude 3 Sonnet (20240229) | 24.6 |
| 5 | DeepSeek R1 | 23.1 |
| 6 | Llama 3.1 405B Instruct | 22.3 |
| 7 | Llama 3.1 70B Instruct | 20 |
| 8 | Claude 3.5 Sonnet (20240620) | 20 |
| 9 | Llama 3.1 8B Instruct | 0 |
Interactive version: theaggregate.ai/benchmark?slug=crmarena-htu-react · How It Works · Data refreshed daily, snapshot 2026-10-09.