diff --git a/.github/workflows/benchmark.yml b/.github/workflows/benchmark.yml
new file mode 100644
index 0000000..b465d51
--- /dev/null
+++ b/.github/workflows/benchmark.yml
@@ -0,0 +1,104 @@
+name: Benchmark
+
+on:
+  push:
+    branches:
+      - master
+    paths:
+      - 'internal/**/*.go'
+      - 'go.mod'
+      - 'go.sum'
+  pull_request:
+    branches:
+      - master
+    paths:
+      - 'internal/**/*.go'
+      - 'go.mod'
+      - 'go.sum'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+
+jobs:
+  benchmark:
+    name: Run Benchmarks
+    runs-on: ubuntu-latest
+    timeout-minutes: 30
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Setup Go
+        uses: actions/setup-go@v5
+        with:
+          go-version-file: 'go.mod'
+          cache: true
+
+      - name: Install benchstat
+        run: go install golang.org/x/perf/cmd/benchstat@latest
+
+      - name: Download dependencies
+        run: go mod download
+
+      - name: Fetch baseline benchmark
+        run: |
+          if git show origin/master:benchmark-baseline.txt >/dev/null 2>&1; then
+            git show origin/master:benchmark-baseline.txt > benchmark-baseline.txt
+            echo "baseline_found=true" >> $GITHUB_ENV
+          else
+            echo "baseline_found=false" >> $GITHUB_ENV
+          fi
+
+      - name: Run benchmarks
+        run: |
+          go test -bench=. -benchmem -count=10 ./... 2>&1 | tee benchmark-current.txt
+
+      - name: Compare benchmarks
+        if: env.baseline_found == 'true'
+        run: |
+          benchstat benchmark-baseline.txt benchmark-current.txt > benchmark-comparison.txt
+          cat benchmark-comparison.txt
+
+      - name: Check for regressions
+        if: env.baseline_found == 'true'
+        run: |
+          if command -v python3 >/dev/null 2>&1; then
+            benchstat benchmark-baseline.txt benchmark-current.txt | \
+              python3 scripts/check_regression.py - \
+              --config .benchmark-thresholds.yaml \
+              --environment ci \
+              || echo "regression_detected=$?" >> $GITHUB_OUTPUT
+          else
+            echo "Python3 not available, skipping regression check"
+          fi
+        id: regression_check
+
+      - name: Save current benchmark as baseline
+        if: github.ref == 'refs/heads/master'
+        run: |
+          cp benchmark-current.txt benchmark-baseline.txt
+          git config user.name "github-actions[bot]"
+          git config user.email "github-actions[bot]@users.noreply.github.com"
+          git add benchmark-baseline.txt || true
+          git commit -m "chore(bench): update benchmark baseline" || true
+          git push || true
+
+      - name: Upload benchmark results
+        uses: actions/upload-artifact@v4
+        with:
+          name: benchmark-results
+          path: |
+            benchmark-current.txt
+            benchmark-baseline.txt
+            benchmark-comparison.txt
+          retention-days: 30
+
+      - name: Fail on regression
+        if: steps.regression_check.outputs.regression_detected == '2'
+        run: |
+          echo "::error::BLOCK level performance regression detected"
+          exit 2
\ No newline at end of file