The AI arena is free today

Open Superagent
AI OrganizationMaintains 2 benchmarks

Salesforce: AI benchmarks & research

Enterprise software company. Salesforce AI Research maintains MCP-Universe and co-authored ChartQA.

Maintained by Salesforce

2 benchmarks

In one line

Salesforce maintains ChartQA (counts toward the LLM Stats Score, 27 models scored) and MCP-Universe (counts toward the LLM Stats Score, 1 model scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about Salesforce.

What is Salesforce?

Enterprise software company. Salesforce AI Research maintains MCP-Universe and co-authored ChartQA. On LLM Stats it maintains 2 benchmarks, led by ChartQA and MCP-Universe. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which Salesforce benchmarks count toward the LLM Stats Score?

ChartQA and MCP-Universe count toward the LLM Stats Score. Only benchmarks admitted to the core set move the main leaderboard; the rest are shown for transparency.

Which models lead Salesforce's benchmarks?

LFM3-VL-2B leads ChartQA at 92.7% (27 models scored) and DeepSeek-V3.2 leads MCP-Universe at 45.9% (1 model scored). Each benchmark page lists the full ranking and how the results were produced.

Where are Salesforce's official benchmark results?

Salesforce's official site is https://www.salesforce.com. Each benchmark page on LLM Stats links to that benchmark's own paper or leaderboard, and shows the scores next to every other benchmark so models can be compared on one page.