diff --git a/pyproject.toml b/pyproject.toml
index 6d95637..ff1f18f 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -7,7 +7,6 @@ requires-python = ">=3.10"
 dependencies = [
     "datasets>=4.4.1",
     "gimkit>=0.1.1",
-    "rich>=14.2.0",
     "vllm>=0.14.0",
 ]
 
diff --git a/src/gimbench/match/evaluators.py b/src/gimbench/match/evaluators.py
index 7ace6fa..a87ae27 100644
--- a/src/gimbench/match/evaluators.py
+++ b/src/gimbench/match/evaluators.py
@@ -134,48 +134,8 @@ def evaluate(self) -> EvalResult:
             evaled_items=evaled_items,
         )
 
-    @staticmethod
-    def print_beautiful_stats(eval_results: EvalResult) -> None:
-        from rich.console import Console
-        from rich.panel import Panel
-        from rich.table import Table
-        from rich.text import Text
-
-        console = Console()
-
-        args = eval_results.args
-        info_text = Text.from_markup(
-            f"[bold]Model:[/bold] [cyan]{args.model_name}[/cyan] "
-            f"[bold]GIM Prompt:[/bold] [green]{args.use_gim_prompt}[/green] "
-            f"[bold]Output Type:[/bold] [magenta]{args.output_type}[/magenta]"
-        )
-        console.print(Panel(info_text, title="Run Arguments", border_style="blue", expand=False))
-
-        table = Table()
-        table.add_column("Tags", justify="right", style="magenta")
-        table.add_column("Predicted", justify="right", style="green")
-        table.add_column("Regex", justify="right", style="blue")
-        table.add_column("Matched", justify="right", style="yellow")
-        table.add_column("Prediction Rate", justify="right", style="green")
-        table.add_column("Match Rate", justify="right", style="yellow")
-        for result in eval_results.evaled_items:
-            pred_rate = f"{result.num_has_prediction / result.num_tags:.2%}" if result.num_tags > 0 else "N/A"
-            match_rate = f"{result.num_regex_match / result.num_regex:.2%}" if result.num_regex > 0 else "N/A"
-
-            table.add_row(
-                str(result.num_tags),
-                str(result.num_has_prediction),
-                str(result.num_regex),
-                str(result.num_regex_match),
-                pred_rate,
-                match_rate,
-            )
-
-        console.print(table)
-
 
 def conduct_eval(args: Namespace, dataset: Dataset):
     evaluator = MatchEvaluator(args, dataset)
     eval_results = evaluator.evaluate()
-    MatchEvaluator.print_beautiful_stats(eval_results)
     eval_results.dump()
diff --git a/uv.lock b/uv.lock
index 5636919..c1151c4 100644
--- a/uv.lock
+++ b/uv.lock
@@ -1324,7 +1324,6 @@ source = { editable = "." }
 dependencies = [
     { name = "datasets" },
     { name = "gimkit" },
-    { name = "rich" },
     { name = "vllm" },
 ]
 
@@ -1339,7 +1338,6 @@ dev = [
 requires-dist = [
     { name = "datasets", specifier = ">=4.4.1" },
     { name = "gimkit", specifier = ">=0.1.1" },
-    { name = "rich", specifier = ">=14.2.0" },
     { name = "vllm", specifier = ">=0.14.0" },
 ]