CRM LLM Leaderboard: leaderboard
Salesforce CRM domain evaluation across 11 enterprise use cases (email generation, call summary, knowledge creation, chat insights) measuring factuality, instruction following, conciseness, completeness, and accuracy.
Metric: CRM Accuracy (0-100). Source: huggingface.co. Saturation forecast: Estimated already saturated. 18 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Claude 3 Opus | 67.5 | #571 |
| 2 | GPT-4o | 66.4 | #343 |
| 3 | Gemini 1.5 Pro | 66.2 | #445 |
| 4 | Command-R+ | 66.2 | #891 |
| 5 | GPT-4 Turbo | 64.6 | #404 |
| 6 | GPT-3.5 Turbo | 62.5 | #865 |
| 7 | Llama 3 70B | 60.3 | #631 |
| 8 | Claude 3 Haiku | 59.4 | #803 |
| 9 | Llama 3 8B | 58.9 | #1242 |
| 10 | Mixtral 8x7B | 58.9 | #1143 |
| 11 | Mistral 7B | 52.9 | #1397 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=crm-llm-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.