Domains: BusinessFinanceLegalMedicalScience
Skills: MultimodalAgenticTool UseKnowledge WorkReasoningWriting

Four-Factor Integrity Breakdown & Primary-Source Evidence

Privacy

Weight 40%
10/10
Access Model: Strictly Private
"Evaluation set: We run a 200-task private set across 10 industry verticals. Each task has a prompt, a set of input files (PDFs, Office documents, spreadsheets and images), and a rubric written by domain experts."

Originality

Weight 25%
10/10
Reuse Profile: All Original (0% reuse)
"Artificial Analysis' implementation of Google DeepMind's Multimodal Knowledge Agent (MKA) benchmark. It tests whether agents can read visually dense project files, such as architectural drawings, engineering schematics and clinical scans, and produce the deliverables a professional would."

Freshness

Weight 20%
10/10
Initial Release: 2026-11Latest Refresh: 2026-11Rolling Updates: No
"November 10, 2026 Multimodal Knowledge Agent (MKA) benchmark: testing knowledge work capabilities with complex visual files"

Grading

Weight 15%
3.3/10
Integrity: Self-Reported / Live NetworkSandbox: live internet
"The agent works in a Linux sandbox that holds the input files and has internet access. It has a code execution tool, web search and page-fetch tools, and an image-viewing tool that we enable only for models that support image inputs."

Frontier Model Standings on MKA (Multimodal Knowledge Agent)

Top 15 active models tracked
Rank Model Official Score Percentile
#1Claude Fable 5.2 max Anthropic0.57 WSR100.0p
#2Gemini 4 Neon xhigh Google0.56 WSR100.0p
#3Gemini 4 Carbon high Google0.54 WSR99.6p
#4Claude Opus 5.5 max Anthropic0.53 WSR95.6p
#5GPT-6.2 Astra max OpenAI0.53 WSR91.5p
#6Claude Sonnet 5.5 max Anthropic0.52 WSR87.4p
#7Gemini 4 Argon high Google0.51 WSR83.3p
#8GPT-6 Astra max OpenAI0.50 WSR79.2p
#9GPT-6.1 Sol max OpenAI0.48 WSR75.1p
#10Muse Wonder max Meta0.47 WSR71.0p
#11Kimi K3.1 Pro max Kimi0.44 WSR66.9p
#12GPT-6.1 Terra max OpenAI0.44 WSR62.8p
#13Claude Haiku 5.5 max Anthropic0.41 WSR58.8p
#14Grok 4.7 xhigh SpaceXAI0.40 WSR54.6p
#15DeepSeek V4.1 Flash 1017 max DeepSeek0.39 WSR50.6p

Embeddable Audit Badge

View Markdown (.md)

Benchmark maintainers can embed this live SVG badge in GitHub READMEs or documentation:

BenchAudit MKA (Multimodal Knowledge Agent) Tier S 9/10
[![BenchAudit Tier S](https://benchaudit.org/badges/mka.svg)](https://benchaudit.org/benchmarks/mka/)