BrowseComp
AssessTools
A benchmark for assessing browser-based agent and multi-step task performance.
Why it's here
Placed in Assess: 2 article(s) of evidence from 3 source(s), led by research-stage coverage, with 0 in the last 30 days. Confidence 50%.
Evidence (2)
- 8Hacker News·9/3/2026model_releaseIFM releases K2 Horizon open model fleet
IFM has released K2 Horizon, a connected fleet of six open models ranging from 0.9B to 375B parameters. The release includes weights, checkpoints, training code, configurations, logs, evaluation results, and data recipes under Apache 2.0, with the smaller models claiming state-of-the-art results in their size classes.
- 7Hugging Face Blog·6/18/2026researchMosaicLeaks exposes privacy risks in deep research agents
Hugging Face describes MosaicLeaks, a new benchmark for evaluating whether deep research agents leak private information when combining local documents with external web search. The paper finds that many agents expose sensitive details through query logs, and that optimizing only for task success can increase leakage; a privacy-aware RL method improves success while reducing leakage.