diff --git a/.github/workflows/test.yml b/.github/workflows/test.yml
index 6faefd1d..85aee29f 100644
--- a/.github/workflows/test.yml
+++ b/.github/workflows/test.yml
@@ -148,6 +148,12 @@ jobs:
           uv run coverage html
           uv run coverage report
 
+      - name: Upload coverage to Codecov
+        uses: codecov/codecov-action@v5
+        with:
+          fail_ci_if_error: false
+          token: ${{ secrets.CODECOV_TOKEN }}
+
       - name: Coverage comment
         if: github.event_name == 'pull_request'
         uses: py-cov-action/python-coverage-comment-action@v3
diff --git a/README.md b/README.md
index 02d87dc0..dea369c6 100644
--- a/README.md
+++ b/README.md
@@ -13,6 +13,7 @@
 [![PyPI version](https://badge.fury.io/py/maseval.svg)](https://badge.fury.io/py/maseval)
 [![Documentation](https://img.shields.io/badge/docs-latest-brightgreen.svg)](https://maseval.readthedocs.io/en/stable/)
 [![Tests](https://github.com/parameterlab/MASEval/actions/workflows/test.yml/badge.svg)](https://github.com/parameterlab/MASEval/actions/workflows/test.yml)
+[![codecov](https://codecov.io/gh/parameterlab/MASEval/graph/badge.svg?token=HMFU71QVB2)](https://codecov.io/gh/parameterlab/MASEval)
 [![License](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
 
 MASEval is an evaluation library that provides a unified interface for benchmarking (multi-)agent systems. It offers standardized abstractions for running any agent implementation—whether built with AutoGen, LangChain, custom frameworks, or direct API calls—against established benchmarks like GAIA and AgentBench, or your own custom evaluation tasks.
diff --git a/pyproject.toml b/pyproject.toml
index 0160b1fa..a3712270 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -79,6 +79,7 @@ all = ["maseval[examples,transformers,wandb]"]
 dev = [
     "pytest>=9.0.0",
     "pytest-cov>=7.0.0",
+    "coverage>=7.0.0",
     "ruff>=0.14.0",
     "ty>=0.0.5",
     "pre-commit>=4.0.0",