diff --git a/mteb/benchmarks/benchmarks/__init__.py b/mteb/benchmarks/benchmarks/__init__.py
index f4b34233db..a240dd3b0f 100644
--- a/mteb/benchmarks/benchmarks/__init__.py
+++ b/mteb/benchmarks/benchmarks/__init__.py
@@ -46,6 +46,16 @@
     MTEB_multilingual_v2,
     RAR_b,
 )
+from mteb.benchmarks.benchmarks.rteb_benchmarks import (
+    RTEB_CODE,
+    RTEB_ENGLISH,
+    RTEB_FINANCE,
+    RTEB_FRENCH,
+    RTEB_GERMAN,
+    RTEB_HEALTHCARE,
+    RTEB_LEGAL,
+    RTEB_MAIN,
+)
 
 __all__ = [
     "Benchmark",
@@ -92,4 +102,12 @@
     "R2MED",
     "VN_MTEB",
     "JINA_VDR",
+    "RTEB_MAIN",
+    "RTEB_FINANCE",
+    "RTEB_LEGAL",
+    "RTEB_CODE",
+    "RTEB_HEALTHCARE",
+    "RTEB_ENGLISH",
+    "RTEB_FRENCH",
+    "RTEB_GERMAN",
 ]
diff --git a/mteb/leaderboard/app.py b/mteb/leaderboard/app.py
index 3c0921ab05..0ec8b91fde 100644
--- a/mteb/leaderboard/app.py
+++ b/mteb/leaderboard/app.py
@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import argparse
 import itertools
 import json
 import logging
@@ -20,6 +21,7 @@
 from mteb.leaderboard.benchmark_selector import (
     BENCHMARK_ENTRIES,
     DEFAULT_BENCHMARK_NAME,
+    RTEB_BENCHMARK_ENTRIES,
     make_selector,
 )
 from mteb.leaderboard.figures import performance_size_plot, radar_chart
@@ -190,7 +192,23 @@ def filter_models(
     return list(models_to_keep)
 
 
+def get_startup_arguments():
+    parser = argparse.ArgumentParser()
+
+    # Add a Boolean flag parameter
+    parser.add_argument(
+        "--show_rteb",
+        action="store_true",
+        help="If set, display RTEB results; otherwise show default results.",
+    )
+
+    return parser.parse_args()
+
+
 def get_leaderboard_app() -> gr.Blocks:
+    args = get_startup_arguments()
+    show_rteb = args.show_rteb
+
     logger.info("Loading all benchmark results")
     all_results = load_results()
 
@@ -277,7 +295,12 @@ def get_leaderboard_app() -> gr.Blocks:
             visible=True,
             width="18%",
         ):
-            benchmark_select, column = make_selector(BENCHMARK_ENTRIES)
+            if show_rteb:
+                benchmark_select, column = make_selector(
+                    BENCHMARK_ENTRIES + RTEB_BENCHMARK_ENTRIES
+                )
+            else:
+                benchmark_select, column = make_selector(BENCHMARK_ENTRIES)
         gr.Markdown(
             """
         ## Embedding Leaderboard
diff --git a/mteb/leaderboard/benchmark_selector.py b/mteb/leaderboard/benchmark_selector.py
index def6ab18f5..8bb10235d7 100644
--- a/mteb/leaderboard/benchmark_selector.py
+++ b/mteb/leaderboard/benchmark_selector.py
@@ -7,6 +7,16 @@
 import mteb
 from mteb import Benchmark
 from mteb.benchmarks.benchmarks import MTEB_multilingual_v2
+from mteb.benchmarks.benchmarks.rteb_benchmarks import (
+    RTEB_CODE,
+    RTEB_ENGLISH,
+    RTEB_FINANCE,
+    RTEB_FRENCH,
+    RTEB_GERMAN,
+    RTEB_HEALTHCARE,
+    RTEB_LEGAL,
+    RTEB_MAIN,
+)
 
 DEFAULT_BENCHMARK_NAME = MTEB_multilingual_v2.name
 
@@ -92,6 +102,29 @@ class MenuEntry:
     ),
 ]
 
+RTEB_BENCHMARK_ENTRIES = [
+    MenuEntry(
+        name="RTEB (Retrieval)",
+        description=None,
+        open=False,
+        benchmarks=[
+            RTEB_MAIN,
+            MenuEntry(
+                "Domain-Specific",
+                description=None,
+                open=False,
+                benchmarks=[RTEB_FINANCE, RTEB_LEGAL, RTEB_CODE, RTEB_HEALTHCARE],
+            ),
+            MenuEntry(
+                "Language-specific",
+                description=None,
+                open=False,
+                benchmarks=[RTEB_ENGLISH, RTEB_FRENCH, RTEB_GERMAN],
+            ),
+        ],
+    )
+]
+
 
 def _create_button(
     i: int,