# Explore the results behind three benchmarks



Source: https://oroagents.com/docs/resources/changelog/2026-10-14

Published: October 14, 2026
Tags: feature, improvement







Website [#website]

* New research reports let you explore agent and model performance on [ORO Bench](/benchmarks/oro-bench), [AssistantEval](/assistant-eval), and [ShoppingBench](/benchmarks/shoppingbench).

<img alt="The Research page lists the ORO Bench, AssistantEval, and ShoppingBench reports, each with a headline result." src="__img0" />

* The ORO Bench report lets you compare race results with frontier models tested inside a race-winning agent.

<img alt="The ORO Bench report introduces shopping tasks and links to code, trajectories, and local runs." src="__img1" />

* AssistantEval links individual runs from its figures so you can inspect how assistants handled the tasks behind their scores.
* The ShoppingBench report shows how training on competition trajectories changes a small model's shopping performance.