cs.AINov 18, 2026

MKA: Evaluating Multimodal Knowledge Agents on end-to-end professional tasks

Authors: Anima Singh, Suhas Yogin, Weicheng Kuo, Ivor Rendulic, Ivan Jurin, Antoine Yang, Oran Kelly, Rohan Doshi, 

Organizations: Google DeepMind

Abstract

We introduce the Multimodal Knowledge Agent (MKA) benchmark, which measures how well autonomous agents perform end-to-end professional knowledge work that depends on visual understanding. Each task requires an agent to extract and combine information from multiple visually dense files, such as CAD blueprints, electronics schematics, radiographs, complex charts and geospatial maps, and to produce a standalone deliverable in .xlsx, .pptx, .pdf, .docx, .html or .png format. Existing benchmarks leave this capability largely untested: removing image-viewing tools leaves Gemini 4 Carbon's score on GDPval unchanged, and single-format evaluations such as GDP.pdf and GDP.xlsx do not require reasoning across files or modalities. MKA contains 200 tasks across 10 economic sectors. Deliverables are graded against expert-weighted rubrics by a sandboxed agentic autorater that agrees with human domain experts on 96.2% of criterion judgments in our expert-graded study (Cohen's κ=0.91κ= 0.91), scored by weighted satisfaction rate (WSR) overall and on frontier criteria unsaturated by prior-generation models (Climb-WSR). Across the frontier models we evaluate (Gemini 4 Carbon, Claude Fable 5.2, Claude Opus 5.5, and GPT-6 Astra), Claude Fable 5.2 (56.6% Climb-WSR, 73.3% Overall WSR) and Gemini 4 Carbon (54.3% Climb-WSR, 71.9% Overall WSR) achieve the highest scores, while Carbon uses 5.7×5.7\times fewer tokens. Even for the strongest models, Climb-WSR remains below 57%, leaving substantial headroom for multimodal agents.

Figures & tables

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

    Feb 26, 2026Zhaochen Su, Jincheng Gao, Hangyu Guo +10Multimodal Agent EvaluationAI Agent Benchmarks

  2. M3^3Exam: Benchmarking Multimodal Memory for Realistic User-Agent Interactions

    Jun 5, 2026Zhengjun Huang, Wenxuan Liu, Zhoujin Tian +6Multimodal UnderstandingMultimodal Grounding