New MKA benchmark: 200 real occupational tasks for multimodal agents

osanseviero · x · 2026-11-17

A new MKA (Multimodal Knowledge Agent) benchmark, built with Artificial Analysis, launches with 200 tasks across 83 occupations, each representing 3–8 hours of expert work. It goes beyond OCR with blueprints, schemas and charts, and requires agents to produce decks, docs and sheets. Open harness and sample tasks are on Hugging Face.

Related event: Google and Artificial Analysis Launch MKA Benchmark for Multimodal Agents(2 posts)→

Original post →

More from Research

Research channel →