The AI arena is free today

Open Superagent
AI OrganizationMaintains 3 benchmarks

Mercor: AI benchmarks & research

Expert-network and evaluation company. Maintains the APEX benchmarks.

Maintained by Mercor

3 benchmarks

In one line

Mercor maintains Apex (counts toward the LLM Stats Score, 2 models scored), APEX-Agents (counts toward the LLM Stats Score, 13 models scored) and APEX-SWE (counts toward the LLM Stats Score, 1 model scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about Mercor.

What is Mercor?

Expert-network and evaluation company. Maintains the APEX benchmarks. On LLM Stats it maintains 3 benchmarks, led by APEX-Agents, Apex and APEX-SWE. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which Mercor benchmarks count toward the LLM Stats Score?

APEX-Agents, Apex and APEX-SWE 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 Mercor's benchmarks?

Kimi K3.1 Pro leads APEX-Agents at 67.2% (13 models scored), Nemotron 3 Ultra (550B A55B) leads Apex at 84.8% (2 models scored) and Grok 4.6 leads APEX-SWE at 56.4% (1 model scored). Each benchmark page lists the full ranking and how the results were produced.

Where are Mercor's official benchmark results?

Mercor's official site is https://mercor.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.