diff --git a/CHANGELOG.md b/CHANGELOG.md
index 1a2df2ec..7376a60c 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -6,6 +6,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/)
 and this project adheres to [Semantic Versioning](https://semver.org/).
 
+## [0.4.1] - 2026-05-23
+### Fixed
+- Fixed several mismatches in task definitions and the provided extra information.
+
 ## [0.4.0] - 2026-05-22
 ### Added
 - Added scripts for rescoring and reproducing the benchmark results based on disclosed trajectories.
diff --git a/pyproject.toml b/pyproject.toml
index f471e259..cabb316e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -4,7 +4,7 @@ build-backend = "hatchling.build"
 
 [project]
 name = "clawbench-eval"
-version = "0.4.0"
+version = "0.4.1"
 description = "Benchmarking framework for evaluating AI web agents on real-world online tasks"
 readme = "README.md"
 requires-python = ">=3.11"
diff --git a/uv.lock b/uv.lock
index f10b531e..de7a0bdc 100644
--- a/uv.lock
+++ b/uv.lock
@@ -58,7 +58,7 @@ wheels = [
 
 [[package]]
 name = "clawbench-eval"
-version = "0.4.0"
+version = "0.4.1"
 source = { editable = "." }
 dependencies = [
     { name = "fpdf2" },