diff --git a/README.md b/README.md
index 2c09dad..66ae6c5 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@ Compare performance results between two Locust runs and show changes relative to
 - Compare any two runs (base vs. current).
 - Parses CSV `report.csv` for aggregated and per-endpoint metrics.
 - Parses per-feature `.html` pages and compares the latest history sample.
-- Outputs human-readable tables or machine-friendly JSON.
+- Outputs human-readable tables, markdown with emoji indicators, or machine-friendly JSON.
 
 ## Requirements
 
@@ -73,10 +73,16 @@ locust-compare test_runs/HTML-Report-292/report.csv test_runs/HTML-Report-294/re
 - JSON output for scripting:
 
 ```bash
-locust-compare test_runs/HTML-Report-292 test_runs/HTML-Report-294 --json
+locust-compare test_runs/HTML-Report-292 test_runs/HTML-Report-294 -o json
 ```
 
-- Colorize output and show verdicts (green=better, red=worse):
+- Markdown output with emoji indicators (✅ better, ❌ worse, ➖ same):
+
+```
+python3 compare_runs.py test_runs/HTML-Report-292 test_runs/HTML-Report-294 -o markdown
+```
+
+- Colorize text output (green=better, red=worse):
 
 ```bash
 locust-compare test_runs/HTML-Report-292 test_runs/HTML-Report-294 --color
@@ -104,9 +110,31 @@ If a metric is not available for an item, it is shown as `-`.
 <img width="598" height="255" alt="image" src="https://github.com/user-attachments/assets/f5394045-6d1e-498e-aa3f-624928ec70a7" />
 
 
+## Markdown Output Example
+
+The `-o markdown` flag produces markdown tables with emoji indicators for verdicts:
+
+```markdown
+## Aggregated
+
+| Metric | Base | Current | Diff | % Change | Verdict |
+| --- | --- | --- | --- | --- | --- |
+| Requests/s | 286.200 | 300 | +13.800 | +4.8% | ✅ |
+| Request Count | 1500 | 1800 | +300 | +20.0% | ✅ |
+| Failure Count | 7 | 4 | -3 | -42.9% | ✅ |
+| Average Response Time | 85.200 | 78.500 | -6.700 | -7.9% | ✅ |
+| 95% | 150 | 140 | -10 | -6.7% | ✅ |
+```
+
+Verdict emojis:
+- ✅ Better performance
+- ❌ Worse performance  
+- ➖ No change
+
+
 ## JSON Schema
 
-The `--json` output is a single JSON object containing keys for each compared item.
+The `-o json` output is a single JSON object containing keys for each compared item.
 
 - CSV items use their request name; the aggregated row is keyed as `Aggregated`.
 - HTML feature pages are keyed as `HTML:<feature_file_stem>`.
diff --git a/compare_runs.py b/compare_runs.py
index 2a0afe5..1c0fcbe 100644
--- a/compare_runs.py
+++ b/compare_runs.py
@@ -333,6 +333,13 @@ def print_section(title: str):
     print("-" * len(title))
 
 
+def print_section_markdown(title: str, level: int = 2):
+    """Print a markdown section header."""
+    print("")
+    print("#" * level + " " + title)
+    print("")
+
+
 def _metric_direction(metric: str) -> str:
     """Return 'higher', 'lower', or 'neutral' for a metric's desirable direction.
 
@@ -365,6 +372,70 @@ def _verdict_for(metric: str, b: Optional[float], c: Optional[float]) -> Optiona
     return None
 
 
+def _verdict_to_emoji(verdict: Optional[str]) -> str:
+    """Convert verdict to emoji for markdown output."""
+    if verdict == "better":
+        return "✅"
+    elif verdict == "worse":
+        return "❌"
+    elif verdict == "same":
+        return "➖"
+    return ""
+
+
+def render_comparison_markdown(
+    base_row: Optional[Row],
+    curr_row: Optional[Row],
+    important_fields: List[str],
+    *,
+    show_verdict: bool = True,
+):
+    """Render comparison as markdown table with emoji indicators."""
+    headers = [
+        "Metric",
+        "Base",
+        "Current",
+        "Diff",
+        "% Change",
+    ]
+    if show_verdict:
+        headers.append("Verdict")
+    rows: List[List[str]] = []
+
+    base_data = base_row.data if base_row else {}
+    curr_data = curr_row.data if curr_row else {}
+
+    fields = important_fields[:]
+    # Also include any extra percentile columns present in data
+    extra_fields = [k for k in curr_data.keys() | base_data.keys() if k.endswith("%") and k not in fields]
+    fields.extend(sorted(extra_fields))
+
+    for field in fields:
+        b = base_data.get(field)
+        c = curr_data.get(field)
+        d = diff(b, c)
+        p = pct_change(b, c)
+        p_str = "-" if p is None else f"{p:+.1f}%"
+        row = [
+            field,
+            format_number(b),
+            format_number(c),
+            ("-" if d is None else (f"{d:+.3f}" if abs(d - round(d)) > 1e-9 else f"{int(d):+d}")),
+            p_str,
+        ]
+        if show_verdict:
+            v = _verdict_for(field, b, c)
+            emoji = _verdict_to_emoji(v)
+            row.append(emoji)
+        rows.append(row)
+
+    # Print markdown table
+    print("| " + " | ".join(headers) + " |")
+    print("| " + " | ".join(["---"] * len(headers)) + " |")
+    for r in rows:
+        print("| " + " | ".join(r) + " |")
+
+
 def render_comparison(
     base_row: Optional[Row],
     curr_row: Optional[Row],
@@ -433,7 +504,7 @@ def render_comparison(
 def compare_reports(
     base_path: Path,
     curr_path: Path,
-    as_json: bool = False,
+    output_format: str = "text",
     *,
     colorize: bool = False,
     show_verdict: bool = True,
@@ -465,7 +536,7 @@ def compare_reports(
     base_html_map = load_html_feature_map(base_path if base_path.is_dir() else base_path.parent)
     curr_html_map = load_html_feature_map(curr_path if curr_path.is_dir() else curr_path.parent)
 
-    if as_json:
+    if output_format == "json":
         # Produce a structured JSON dict
         out: Dict[str, Dict[str, Dict[str, Optional[float]]]] = {}
         for key in all_keys:
@@ -517,45 +588,85 @@ def compare_reports(
         return 0
 
     # Human readable output
-    print_section("Aggregated")
-    render_comparison(
-        base_idx.get("__Aggregated__"),
-        curr_idx.get("__Aggregated__"),
-        important_fields,
-        colorize=colorize,
-        show_verdict=show_verdict,
-    )
+    if output_format == "markdown":
+        print("# Locust Performance Comparison")
+        print("")
+        print_section_markdown("Aggregated", 2)
+        render_comparison_markdown(
+            base_idx.get("__Aggregated__"),
+            curr_idx.get("__Aggregated__"),
+            important_fields,
+            show_verdict=show_verdict,
+        )
 
-    endpoint_keys = [k for k in all_keys if k != "__Aggregated__"]
-    for ek in endpoint_keys:
-        title = f"Endpoint: {ek}"
-        print_section(title)
+        endpoint_keys = [k for k in all_keys if k != "__Aggregated__"]
+        for ek in endpoint_keys:
+            title = f"Endpoint: {ek}"
+            print_section_markdown(title, 3)
+            render_comparison_markdown(
+                base_idx.get(ek),
+                curr_idx.get(ek),
+                important_fields,
+                show_verdict=show_verdict,
+            )
+
+        # Render HTML features
+        feature_keys = sorted(set(base_html_map.keys()) | set(curr_html_map.keys()))
+        if feature_keys:
+            print_section_markdown("HTML Features", 2)
+            for fk in feature_keys:
+                print_section_markdown(f"Feature: {fk}", 3)
+                b_map = base_html_map.get(fk, {})
+                c_map = curr_html_map.get(fk, {})
+                ep_keys = sorted(set(b_map.keys()) | set(c_map.keys()))
+                for ep in ep_keys:
+                    print_section_markdown(f"Endpoint: {ep}", 4)
+                    render_comparison_markdown(
+                        b_map.get(ep),
+                        c_map.get(ep),
+                        important_fields,
+                        show_verdict=show_verdict,
+                    )
+    else:
+        print_section("Aggregated")
         render_comparison(
-            base_idx.get(ek),
-            curr_idx.get(ek),
+            base_idx.get("__Aggregated__"),
+            curr_idx.get("__Aggregated__"),
             important_fields,
             colorize=colorize,
             show_verdict=show_verdict,
         )
 
-    # Render HTML features
-    feature_keys = sorted(set(base_html_map.keys()) | set(curr_html_map.keys()))
-    if feature_keys:
-        print_section("HTML Features")
-        for fk in feature_keys:
-            print_section(f"Feature: {fk}")
-            b_map = base_html_map.get(fk, {})
-            c_map = curr_html_map.get(fk, {})
-            ep_keys = sorted(set(b_map.keys()) | set(c_map.keys()))
-            for ep in ep_keys:
-                print_section(f"Endpoint: {ep}")
-                render_comparison(
-                    b_map.get(ep),
-                    c_map.get(ep),
-                    important_fields,
-                    colorize=colorize,
-                    show_verdict=show_verdict,
-                )
+        endpoint_keys = [k for k in all_keys if k != "__Aggregated__"]
+        for ek in endpoint_keys:
+            title = f"Endpoint: {ek}"
+            print_section(title)
+            render_comparison(
+                base_idx.get(ek),
+                curr_idx.get(ek),
+                important_fields,
+                colorize=colorize,
+                show_verdict=show_verdict,
+            )
+
+        # Render HTML features
+        feature_keys = sorted(set(base_html_map.keys()) | set(curr_html_map.keys()))
+        if feature_keys:
+            print_section("HTML Features")
+            for fk in feature_keys:
+                print_section(f"Feature: {fk}")
+                b_map = base_html_map.get(fk, {})
+                c_map = curr_html_map.get(fk, {})
+                ep_keys = sorted(set(b_map.keys()) | set(c_map.keys()))
+                for ep in ep_keys:
+                    print_section(f"Endpoint: {ep}")
+                    render_comparison(
+                        b_map.get(ep),
+                        c_map.get(ep),
+                        important_fields,
+                        colorize=colorize,
+                        show_verdict=show_verdict,
+                    )
 
     return 0
 
@@ -569,11 +680,17 @@ def main():
     )
     parser.add_argument("base", type=Path, help="Base run directory or report.csv path")
     parser.add_argument("current", type=Path, help="Current run directory or report.csv path")
-    parser.add_argument("--json", action="store_true", help="Output results as JSON")
+    parser.add_argument(
+        "-o",
+        "--output",
+        choices=["text", "json", "markdown"],
+        default="text",
+        help="Output format: text (default), json, or markdown with emoji indicators (✅ better, ❌ worse, ➖ same)",
+    )
     parser.add_argument(
         "--color",
         action="store_true",
-        help="Colorize rows: green if better, red if worse",
+        help="Colorize rows: green if better, red if worse (only for text output)",
     )
     parser.add_argument(
         "--no-verdict",
@@ -587,7 +704,7 @@ def main():
         return compare_reports(
             args.base,
             args.current,
-            as_json=args.json,
+            output_format=args.output,
             colorize=args.color,
             show_verdict=args.show_verdict,
         )
diff --git a/tests/test_compare_reports.py b/tests/test_compare_reports.py
index 7919c5f..54cd875 100644
--- a/tests/test_compare_reports.py
+++ b/tests/test_compare_reports.py
@@ -15,7 +15,7 @@ class TestCompareReportsJson:
     """Tests for compare_reports with JSON output."""
 
     def test_json_output_structure(self, temp_test_dir, temp_test_dir_v2, capsys):
-        result = compare_reports(temp_test_dir, temp_test_dir_v2, as_json=True)
+        result = compare_reports(temp_test_dir, temp_test_dir_v2, output_format="json")
         assert result == 0
 
         captured = capsys.readouterr()
@@ -27,7 +27,7 @@ def test_json_output_structure(self, temp_test_dir, temp_test_dir_v2, capsys):
         assert "/api/login" in data
 
     def test_json_output_metrics(self, temp_test_dir, temp_test_dir_v2, capsys):
-        compare_reports(temp_test_dir, temp_test_dir_v2, as_json=True)
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="json")
 
         captured = capsys.readouterr()
         data = json.loads(captured.out)
@@ -42,7 +42,7 @@ def test_json_output_metrics(self, temp_test_dir, temp_test_dir_v2, capsys):
         assert "pct_change" in metric
 
     def test_json_output_values(self, temp_test_dir, temp_test_dir_v2, capsys):
-        compare_reports(temp_test_dir, temp_test_dir_v2, as_json=True)
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="json")
 
         captured = capsys.readouterr()
         data = json.loads(captured.out)
@@ -61,7 +61,7 @@ class TestCompareReportsHuman:
     """Tests for compare_reports with human-readable output."""
 
     def test_human_output_includes_sections(self, temp_test_dir, temp_test_dir_v2, capsys):
-        result = compare_reports(temp_test_dir, temp_test_dir_v2, as_json=False)
+        result = compare_reports(temp_test_dir, temp_test_dir_v2, output_format="text")
         assert result == 0
 
         captured = capsys.readouterr()
@@ -72,7 +72,7 @@ def test_human_output_includes_sections(self, temp_test_dir, temp_test_dir_v2, c
         assert "Endpoint:" in output
 
     def test_human_output_includes_metrics(self, temp_test_dir, temp_test_dir_v2, capsys):
-        compare_reports(temp_test_dir, temp_test_dir_v2, as_json=False)
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="text")
 
         captured = capsys.readouterr()
         output = captured.out
@@ -83,7 +83,7 @@ def test_human_output_includes_metrics(self, temp_test_dir, temp_test_dir_v2, ca
         assert "Average Response Time" in output
 
     def test_human_output_includes_verdict(self, temp_test_dir, temp_test_dir_v2, capsys):
-        compare_reports(temp_test_dir, temp_test_dir_v2, as_json=False, show_verdict=True)
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="text", show_verdict=True)
 
         captured = capsys.readouterr()
         output = captured.out
@@ -94,7 +94,7 @@ def test_human_output_includes_verdict(self, temp_test_dir, temp_test_dir_v2, ca
         assert "better" in output or "worse" in output or "same" in output
 
     def test_human_output_no_verdict(self, temp_test_dir, temp_test_dir_v2, capsys):
-        compare_reports(temp_test_dir, temp_test_dir_v2, as_json=False, show_verdict=False)
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="text", show_verdict=False)
 
         captured = capsys.readouterr()
         output = captured.out
@@ -105,7 +105,7 @@ def test_human_output_no_verdict(self, temp_test_dir, temp_test_dir_v2, capsys):
         assert "Verdict" not in header_line
 
     def test_human_output_colorize(self, temp_test_dir, temp_test_dir_v2, capsys):
-        compare_reports(temp_test_dir, temp_test_dir_v2, as_json=False, colorize=True)
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="text", colorize=True)
 
         captured = capsys.readouterr()
         output = captured.out
@@ -119,7 +119,7 @@ class TestCompareReportsEdgeCases:
 
     def test_compare_same_report(self, temp_test_dir, capsys):
         """Comparing a report to itself should show no changes."""
-        compare_reports(temp_test_dir, temp_test_dir, as_json=True)
+        compare_reports(temp_test_dir, temp_test_dir, output_format="json")
 
         captured = capsys.readouterr()
         data = json.loads(captured.out)
@@ -141,7 +141,7 @@ def test_compare_with_missing_endpoint(self, sample_csv_content, sample_csv_cont
             base_path.write_text(base_csv)
             curr_path.write_text(sample_csv_content_v2)
 
-            compare_reports(Path(base_dir), Path(curr_dir), as_json=True)
+            compare_reports(Path(base_dir), Path(curr_dir), output_format="json")
 
             captured = capsys.readouterr()
             data = json.loads(captured.out)
@@ -164,7 +164,7 @@ def test_compare_with_new_endpoint(self, sample_csv_content, sample_csv_content_
             base_path.write_text(sample_csv_content)
             curr_path.write_text(curr_csv)
 
-            compare_reports(Path(base_dir), Path(curr_dir), as_json=True)
+            compare_reports(Path(base_dir), Path(curr_dir), output_format="json")
 
             captured = capsys.readouterr()
             data = json.loads(captured.out)
@@ -195,7 +195,7 @@ def test_json_includes_html_features(self, temp_dir_with_html, capsys):
                 if html_file.name != "htmlpublisher-wrapper.html":
                     shutil.copy(html_file, other / html_file.name)
 
-            compare_reports(temp_dir_with_html, other, as_json=True)
+            compare_reports(temp_dir_with_html, other, output_format="json")
 
             captured = capsys.readouterr()
             data = json.loads(captured.out)
@@ -218,7 +218,7 @@ def test_human_output_includes_html_section(self, temp_dir_with_html, capsys):
                 if html_file.name != "htmlpublisher-wrapper.html":
                     shutil.copy(html_file, other / html_file.name)
 
-            compare_reports(temp_dir_with_html, other, as_json=False)
+            compare_reports(temp_dir_with_html, other, output_format="text")
 
             captured = capsys.readouterr()
             output = captured.out
@@ -238,7 +238,7 @@ def test_compare_real_reports(self, real_test_runs_path, capsys):
         if not base.exists() or not curr.exists():
             pytest.skip("Real test data not available")
 
-        result = compare_reports(base, curr, as_json=True)
+        result = compare_reports(base, curr, output_format="json")
         assert result == 0
 
         captured = capsys.readouterr()
diff --git a/tests/test_markdown_output.py b/tests/test_markdown_output.py
new file mode 100644
index 0000000..901c185
--- /dev/null
+++ b/tests/test_markdown_output.py
@@ -0,0 +1,187 @@
+"""Tests for markdown output functionality."""
+import pytest
+import sys
+import json
+import tempfile
+from pathlib import Path
+from io import StringIO
+
+sys.path.insert(0, str(Path(__file__).parent.parent))
+from compare_runs import compare_reports, _verdict_to_emoji
+
+
+class TestMarkdownOutput:
+    """Tests for markdown output functionality."""
+
+    def test_verdict_to_emoji_better(self):
+        """Test emoji for 'better' verdict."""
+        assert _verdict_to_emoji("better") == "✅"
+
+    def test_verdict_to_emoji_worse(self):
+        """Test emoji for 'worse' verdict."""
+        assert _verdict_to_emoji("worse") == "❌"
+
+    def test_verdict_to_emoji_same(self):
+        """Test emoji for 'same' verdict."""
+        assert _verdict_to_emoji("same") == "➖"
+
+    def test_verdict_to_emoji_none(self):
+        """Test emoji for None verdict."""
+        assert _verdict_to_emoji(None) == ""
+
+    def test_markdown_output_structure(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test that markdown output has correct structure."""
+        result = compare_reports(temp_test_dir, temp_test_dir_v2, output_format="markdown")
+        assert result == 0
+
+        captured = capsys.readouterr()
+        output = captured.out
+
+        # Should have markdown headers
+        assert "# Locust Performance Comparison" in output
+        assert "## Aggregated" in output
+        assert "### Endpoint:" in output
+
+        # Should have markdown table syntax
+        assert "|" in output
+        assert "---" in output
+
+    def test_markdown_output_includes_metrics(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test that markdown output includes all expected metrics."""
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="markdown")
+
+        captured = capsys.readouterr()
+        output = captured.out
+
+        # Should have metric names in tables
+        assert "Requests/s" in output
+        assert "Request Count" in output
+        assert "Average Response Time" in output
+        assert "95%" in output
+
+    def test_markdown_output_includes_emojis(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test that markdown output includes emoji indicators."""
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="markdown", show_verdict=True)
+
+        captured = capsys.readouterr()
+        output = captured.out
+
+        # Should have emoji indicators for verdicts
+        assert "✅" in output or "❌" in output or "➖" in output
+
+    def test_markdown_output_no_verdict(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test markdown output without verdict column."""
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="markdown", show_verdict=False)
+
+        captured = capsys.readouterr()
+        output = captured.out
+
+        # Should NOT have Verdict column in tables
+        lines = output.split('\n')
+        header_lines = [l for l in lines if 'Metric' in l and '|' in l]
+        assert len(header_lines) > 0
+        for header in header_lines:
+            assert "Verdict" not in header
+
+    def test_markdown_output_no_color_codes(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test that markdown output does not contain ANSI color codes."""
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="markdown")
+
+        captured = capsys.readouterr()
+        output = captured.out
+
+        # Should NOT have ANSI color codes
+        assert "\033[32m" not in output
+        assert "\033[31m" not in output
+        assert "\033[0m" not in output
+
+    def test_markdown_table_format(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test that markdown tables are properly formatted."""
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="markdown", show_verdict=True)
+
+        captured = capsys.readouterr()
+        output = captured.out
+        lines = output.split('\n')
+
+        # Find table lines
+        table_lines = [l for l in lines if l.startswith('|') and 'Metric' in l]
+        assert len(table_lines) > 0
+
+        # Check that separator line follows header
+        for i, line in enumerate(lines):
+            if 'Metric' in line and line.startswith('|'):
+                # Next line should be separator
+                if i + 1 < len(lines):
+                    next_line = lines[i + 1]
+                    assert '---' in next_line
+                    assert next_line.startswith('|')
+
+    def test_markdown_with_html_features(self, temp_dir_with_html, capsys):
+        """Test markdown output includes HTML features section."""
+        with tempfile.TemporaryDirectory() as other_dir:
+            other = Path(other_dir)
+            (other / "report.csv").write_text("""Type,Name,Request Count
+GET,/api/test,100
+,Aggregated,100
+""")
+            # Copy the HTML file
+            import shutil
+            for html_file in temp_dir_with_html.glob("*.html"):
+                if html_file.name != "htmlpublisher-wrapper.html":
+                    shutil.copy(html_file, other / html_file.name)
+
+            compare_reports(temp_dir_with_html, other, output_format="markdown")
+
+            captured = capsys.readouterr()
+            output = captured.out
+
+            # Should have HTML Features section
+            assert "## HTML Features" in output
+            assert "### Feature:" in output
+
+    def test_markdown_output_values(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test that markdown output contains correct values."""
+        compare_reports(temp_test_dir, temp_test_dir_v2, output_format="markdown")
+
+        captured = capsys.readouterr()
+        output = captured.out
+
+        # Should contain values from both base and current
+        assert "1000" in output  # base request count
+        assert "1200" in output  # current request count
+
+
+class TestMarkdownCompatibility:
+    """Test that markdown output doesn't break existing functionality."""
+
+    def test_json_still_works(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test that JSON output is not affected by markdown changes."""
+        result = compare_reports(temp_test_dir, temp_test_dir_v2, output_format="json")
+        assert result == 0
+
+        captured = capsys.readouterr()
+        data = json.loads(captured.out)
+        assert "__Aggregated__" in data
+
+    def test_normal_output_still_works(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test that normal human-readable output still works."""
+        result = compare_reports(temp_test_dir, temp_test_dir_v2, output_format="text")
+        assert result == 0
+
+        captured = capsys.readouterr()
+        output = captured.out
+
+        # Should have section headers without markdown syntax
+        assert "Aggregated" in output
+        assert "# Locust" not in output  # No markdown headers
+
+    def test_color_output_still_works(self, temp_test_dir, temp_test_dir_v2, capsys):
+        """Test that colorized output still works."""
+        result = compare_reports(temp_test_dir, temp_test_dir_v2, output_format="text", colorize=True)
+        assert result == 0
+
+        captured = capsys.readouterr()
+        output = captured.out
+
+        # Should have ANSI color codes
+        assert "\033[32m" in output or "\033[31m" in output
diff --git a/tests/test_zip_support.py b/tests/test_zip_support.py
index b7445a7..7ffe4e3 100644
--- a/tests/test_zip_support.py
+++ b/tests/test_zip_support.py
@@ -112,7 +112,7 @@ def test_compare_zip_to_zip(self, sample_csv_content, sample_csv_content_v2, cap
             with zipfile.ZipFile(curr_zip, "w") as zf:
                 zf.writestr("report.csv", sample_csv_content_v2)
 
-            result = compare_reports(base_zip, curr_zip, as_json=True)
+            result = compare_reports(base_zip, curr_zip, output_format="json")
             assert result == 0
 
             captured = capsys.readouterr()
@@ -126,7 +126,7 @@ def test_compare_zip_to_directory(self, sample_csv_content, temp_test_dir_v2, ca
             with zipfile.ZipFile(base_zip, "w") as zf:
                 zf.writestr("report.csv", sample_csv_content)
 
-            result = compare_reports(base_zip, temp_test_dir_v2, as_json=True)
+            result = compare_reports(base_zip, temp_test_dir_v2, output_format="json")
             assert result == 0
 
     def test_compare_directory_to_zip(self, temp_test_dir, sample_csv_content_v2, capsys):
@@ -137,7 +137,7 @@ def test_compare_directory_to_zip(self, temp_test_dir, sample_csv_content_v2, ca
             with zipfile.ZipFile(curr_zip, "w") as zf:
                 zf.writestr("report.csv", sample_csv_content_v2)
 
-            result = compare_reports(temp_test_dir, curr_zip, as_json=True)
+            result = compare_reports(temp_test_dir, curr_zip, output_format="json")
             assert result == 0
 
     def test_zip_with_nested_directory_structure(self, sample_csv_content, sample_csv_content_v2, capsys):
@@ -152,7 +152,7 @@ def test_zip_with_nested_directory_structure(self, sample_csv_content, sample_cs
             with zipfile.ZipFile(curr_zip, "w") as zf:
                 zf.writestr("HTML-Report-200/report.csv", sample_csv_content_v2)
 
-            result = compare_reports(base_zip, curr_zip, as_json=True)
+            result = compare_reports(base_zip, curr_zip, output_format="json")
             assert result == 0
 
     def test_zip_with_html_files(self, sample_csv_content, sample_html_template_args, capsys):
@@ -169,7 +169,7 @@ def test_zip_with_html_files(self, sample_csv_content, sample_html_template_args
                 zf.writestr("report.csv", sample_csv_content)
                 zf.writestr("feature_test.html", sample_html_template_args)
 
-            result = compare_reports(base_zip, curr_zip, as_json=True)
+            result = compare_reports(base_zip, curr_zip, output_format="json")
             assert result == 0
 
             captured = capsys.readouterr()