CRMArena - NED (ReAct): leaderboard

Metric: Exact match (%). Source: arxiv.org. Saturation forecast: Estimated already saturated. 9 models tracked.

Top models

#ModelScore
1Claude 3.5 Sonnet (20240620)52.3
2DeepSeek R140.8
3O1 (2024-12-17)34.6
4Llama 3.1 405B Instruct33.9
5Llama 3.1 70B Instruct33.1
6GPT-4o Mini31.5
7GPT-4o (2024-08-06)30.8
8Claude 3 Sonnet (20240229)29.2
9Llama 3.1 8B Instruct6.2

Interactive version: theaggregate.ai/benchmark?slug=crmarena-ned-react · How It Works · Data refreshed daily, snapshot 2026-10-09.