---
title: "v0.3.0"
description: "Released April 2, 2026."
type: changelog
date: 2026-04-02T00:00:03.000Z
slug: changelog/0.3.0
---

- Added a thin native DAPO adapter with reward/config helpers for verl-style training recipes
- Hardened imported benchmark loading so nested HumanEval/MBPP-style benchmark registries resolve predictably
- Fixed benchmark alias and task-id routing for imported suites such as `humaneval` and `HumanEval/0`
- Made mixed benchmark routing stricter and rejected mismatched per-sample batch metadata instead of silently broadcasting it
- Restored Python 3.10 compatibility in the release/test matrix