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)→
More from Research
- Google DeepMind unveils Gemini 4 Carbon for physics, math and life science research — GoogleDeepMind · 2026-11-17
- Gemini 4 Carbon proves Signal crypto security in weeks, finds 40x more protein sequences — GoogleDeepMind · 2026-11-17
- Frame-by-frame real gradient descent: α=0.6 zigzags the valley, α=0.3 glides down — ZeroStateReflex · 2026-11-17
- Data Scientist Distills 2 Years of Bayesian Statistics Lessons Into a 2-Minute Primer — mdancho84 · 2026-11-17
- 'Formalizing All Math' went from absurd to consensus in 8 months; CFSG audit found 96 paper errors — AlexKontorovich · 2026-11-17
- Chest X-ray AI flags high fracture risk in 53k-patient NEJM AI study — zakkohane · 2026-11-17