HOT RADAR
agentHEAT 28.6°

AI CURATED HOT STORY · 11/11/2026

Google DeepMind Launches MKA Benchmark for Multimodal Knowledge Agents

2 reports archived1 independent sourcesupdated 11/11/2026, 02:28:22
Synthesis & Latest Updates
1 Sources Cross-Validated

Google DeepMind, in partnership with Artificial Analysis, launched the Multimodal Knowledge Agent (MKA) evaluation, a benchmark of 200 private real-world visual tasks spanning 10 industries. Agents must interpret dense visual files such as architectural drawings, engineering schematics and clinical scans, then produce deliverables including slide decks, spreadsheets and reports. Scoring uses expert rubrics split into Climb and Regression criteria, averaging about 70 weighted items per task, with Claude Sonnet 5.5 leading in several domains.

LATEST/Google DeepMind, in partnership with Artificial Analysis, launched the Multimodal Knowledge Agent (MKA) evaluation, a benchmark of 200 private real-world visual tasks spanning 10 industries. Agents must interpret dense visual files such as architectural drawings, engineering schematics and clinical scans, then produce deliverables including slide decks, spreadsheets and reports. Scoring uses expert rubrics split into Climb and Regression criteria, averaging about 70 weighted items per task, with Claude Sonnet 5.5 leading in several domains.

Hourly heat curve

3 fully observed hours
Now
28.6
Peak
29.603:00
24h change
–

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 2 reports · Latest first
  1. Artificial Analysis (@ArtificialAnlys)T1·58 pts
    • MKA targets real professional visual tasks like blueprint cross-referencing and scientific chart reading, unlike text-only evaluations
    • Gemini 4 Carbon ranks second at one-sixth the average cost per task of the top model
    • The benchmark was co-built by DeepMind and Artificial Analysis and is now integrated into the Artificial Analysis platform