Spaces:
Runtime error
Runtime error
refine
Browse files
app.py
CHANGED
@@ -371,13 +371,13 @@ with gr.Blocks() as app:
|
|
371 |
with gr.Tab("⚔️Arena"):
|
372 |
# Add title and description as a Markdown component
|
373 |
arena_intro = gr.Markdown(
|
374 |
-
"""
|
375 |
# ⚔️ Software Engineering (SE) Arena: Explore and Test the Best SE Chatbots with Long-Context Interactions
|
376 |
|
377 |
## 📜How It Works
|
378 |
-
- **Blind Comparison**: Submit
|
379 |
-
- **Interactive Voting**: Engage in multi-turn dialogues and compare responses.
|
380 |
-
- **Fair Play Rules**: Votes are
|
381 |
|
382 |
**Note:** Due to budget constraints, responses that take longer than one minute to generate will be discarded.
|
383 |
""",
|
|
|
371 |
with gr.Tab("⚔️Arena"):
|
372 |
# Add title and description as a Markdown component
|
373 |
arena_intro = gr.Markdown(
|
374 |
+
f"""
|
375 |
# ⚔️ Software Engineering (SE) Arena: Explore and Test the Best SE Chatbots with Long-Context Interactions
|
376 |
|
377 |
## 📜How It Works
|
378 |
+
- **Blind Comparison**: Submit a software engineering-related query to two anonymous chatbots randomly selected from up to {len(available_models)} top models, including ChatGPT, Gemini, Claude, Llama, and others.
|
379 |
+
- **Interactive Voting**: Engage in multi-turn dialogues with both chatbots and compare their responses. You can continue the conversation until you confidently choose the better model.
|
380 |
+
- **Fair Play Rules**: Votes are counted only if chatbot identities remain anonymous. Revealing a chatbot's identity disqualifies the session.
|
381 |
|
382 |
**Note:** Due to budget constraints, responses that take longer than one minute to generate will be discarded.
|
383 |
""",
|