Remove placeholder text

app.py

@@ -113,8 +113,8 @@ with demo:
         with gr.TabItem("About", elem_classes="llm-benchmark-tab-table", id=2):
             gr.Markdown(ABOUT_TEXT, elem_classes="markdown-text", sanitize_html=False)
 
-        with gr.TabItem("Reproducibility", elem_classes="llm-benchmark-tab-table", id=3):
-            gr.Markdown(REPRODUCIBILITY_TEXT, elem_classes="markdown-text", sanitize_html=False)
+        # with gr.TabItem("Reproducibility", elem_classes="llm-benchmark-tab-table", id=3):
+        #     gr.Markdown(REPRODUCIBILITY_TEXT, elem_classes="markdown-text", sanitize_html=False)
 
 assets = [black_logo_path, white_logo_path]
 demo.launch(allowed_paths=assets)

src/about.py

@@ -1,4 +1,3 @@
-
 # Your leaderboard name
 TITLE = """<h1 align="center" id="space-title">Evaluation Leaderboard</h1>"""
 
@@ -33,20 +32,20 @@ These benchmarks assess fundamental reasoning and knowledge capabilities of mode
 
 <div class="benchmark-table-container">
 
-| Benchmark           | Description                                                                      | Domain                                  |
-|--------------------|----------------------------------------------------------------------------------|-----------------------------------------------|
-| **ARC-Easy** / **ARC-Challenge** | Multiple-choice science questions measuring scientific & commonsense reasoning. | Example  |
-| **DROP**             | Reading comprehension benchmark emphasizing discrete reasoning steps.             | Example |
-| **WinoGrande**        | Commonsense reasoning challenge focused on co-reference resolution.             | Example |
-| **GSM8K**             | Grade-school math word problems testing arithmetic & multi-step reasoning.         | Example |
-| **HellaSwag**        | Commonsense inference task centered on action completion.                        |  Example |
-| **HumanEval**         | Evaluates code generation and reasoning in a programming context.                |  Example |
-| **IFEval**            | Specialized benchmark for incremental formal reasoning.                          |  Example |
-| **IFEval**            | Specialized benchmark for incremental formal reasoning.                          |  Example |
-| **MATH**              | High school-level math questions requiring detailed solutions.                  |  Example |
-| **MMLU** / **MMLU-Pro**| Multi-subject multiple-choice tests of advanced knowledge.                     |  Example |
-| **GPQA-Diamond**      | Question-answering benchmark assessing deeper reasoning & knowledge linking.      |  Example |
-| **MMMU** (Multi-Choice / Open-Ended) | Multilingual & multi-domain tasks testing structured & open responses.   |  Example |
+| Benchmark           | Description                                                                      |
+|--------------------|----------------------------------------------------------------------------------|
+| **ARC-Easy** / **ARC-Challenge** | Multiple-choice science questions measuring scientific & commonsense reasoning. |
+| **DROP**             | Reading comprehension benchmark emphasizing discrete reasoning steps.             |
+| **WinoGrande**        | Commonsense reasoning challenge focused on co-reference resolution.             |
+| **GSM8K**             | Grade-school math word problems testing arithmetic & multi-step reasoning.         |
+| **HellaSwag**        | Commonsense inference task centered on action completion.                        |
+| **HumanEval**         | Evaluates code generation and reasoning in a programming context.                |
+| **IFEval**            | Specialized benchmark for incremental formal reasoning.                          |
+| **IFEval**            | Specialized benchmark for incremental formal reasoning.                          |
+| **MATH**              | High school-level math questions requiring detailed solutions.                  |
+| **MMLU** / **MMLU-Pro**| Multi-subject multiple-choice tests of advanced knowledge.                     |
+| **GPQA-Diamond**      | Question-answering benchmark assessing deeper reasoning & knowledge linking.      |
+| **MMMU** (Multi-Choice / Open-Ended) | Multilingual & multi-domain tasks testing structured & open responses.   |
 </div>
 
 ### 🚀 Agentic Benchmarks
@@ -55,14 +54,13 @@ These benchmarks go beyond basic reasoning and evaluate more advanced, autonomou
 
 <div class="benchmark-table-container">
 
-| Benchmark              | Description                                                                 | Key Skills                                      |
-|-----------------------|-----------------------------------------------------------------------------|-------------------------------------------------|
-| **GAIA**                | Evaluates autonomous reasoning, planning, problem-solving, & multi-turn interactions. |  Example |
-| [**InterCode-CTF**](https://ukgovernmentbeis.github.io/inspect_evals/evals/cybersecurity/in_house_ctf/)   | Capture-the-flag challenge focused on code interpretation & debugging.       |  Example |
-| **GDM-In-House-CTF**    | Capture-the-flag challenge testing web application security skills.         |  Example |
-| **AgentHarm** / **AgentHarm-Benign** | Measures harmfulness of LLM agents (and benign behavior baseline).   |  Example |
-| **SWE-Bench**           | Tests AI agent ability to solve software engineering tasks.                 |  Example |
-
+| Benchmark              | Description                                                                 |
+|-----------------------|----------------------------------------------------------------------------|
+| **GAIA**                | Evaluates autonomous reasoning, planning, problem-solving, & multi-turn interactions. |
+| [**InterCode-CTF**](https://ukgovernmentbeis.github.io/inspect_evals/evals/cybersecurity/in_house_ctf/)   | Capture-the-flag challenge focused on code interpretation & debugging.       |
+| **GDM-In-House-CTF**    | Capture-the-flag challenge testing web application security skills.         |
+| **AgentHarm** / **AgentHarm-Benign** | Measures harmfulness of LLM agents (and benign behavior baseline).   |
+| **SWE-Bench**           | Tests AI agent ability to solve software engineering tasks.                 |
 </div>
 """