Google DeepMind, in partnership with Artificial Analysis
Multimodal Knowledge Agent Benchmark
Google DeepMind's benchmark of professional knowledge work where the key information sits in visual files such as architectural drawings, engineering schematics and medical scans. The agent has to deliver a finished report, spreadsheet, slide deck or marked-up drawing. Artificial Analysis runs it on a private 200-task set.
ModelsModels with a result.19
Top-3 spreadPoints from first to third.3.6 pts
YearYear of release.2026
Result and price
19 of 19 results
Results
19 results#ModelResultThe score from the source.
