Google and Artificial Analysis launch MKA benchmark
What happened
On November 11, 2026, Google announced on its Gemini blog that it co-launched the Multimodal Knowledge Agent (MKA) benchmark with Artificial Analysis. The benchmark evaluates how well agents handle visually complex documents and complete real knowledge-work tasks, with the focus on multimodal document handling and knowledge-work tasks. Reports so far cover only the launch, with no test results, model scores or update plans disclosed.
Written by AI from the coverage · updated yesterday
Coverage
Follow the reports to see the story from different sides.
- Google Blog · GeminiIntroducing the Multimodal Knowledge Agent benchmark
Google 与 Artificial Analysis 推出 Multimodal Knowledge Agent（MKA）基准，评估智能体处理视觉复杂文件、完成真实知识工作任务的能力。
Heat over time
Heat now 4·Comparable peak 10（Nov 11 01:00）·Comparable change over 24 hours -51%
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.