Spaces:
Running
Running
Fix typos in SWE Arena references to SWE-Arena
Browse files
app.py
CHANGED
|
@@ -561,7 +561,7 @@ with gr.Blocks() as app:
|
|
| 561 |
leaderboard_intro = gr.Markdown(
|
| 562 |
"""
|
| 563 |
# 🏆 FM4SE Leaderboard: Community-Driven Evaluation of Top Foundation Models (FMs) in Software Engineering (SE) Tasks
|
| 564 |
-
The SWE
|
| 565 |
""",
|
| 566 |
elem_classes="leaderboard-intro",
|
| 567 |
)
|
|
@@ -590,10 +590,10 @@ with gr.Blocks() as app:
|
|
| 590 |
# Add a citation block in Markdown
|
| 591 |
citation_component = gr.Markdown(
|
| 592 |
"""
|
| 593 |
-
Made with ❤️ for SWE
|
| 594 |
```
|
| 595 |
@inproceedings{zhao2025se,
|
| 596 |
-
title={SWE
|
| 597 |
author={Zhao, Zhimin},
|
| 598 |
booktitle={ACM international conference on AI Foundation Models and Software Engineering},
|
| 599 |
year={2025}}
|
|
@@ -604,7 +604,7 @@ with gr.Blocks() as app:
|
|
| 604 |
# Add title and description as a Markdown component
|
| 605 |
arena_intro = gr.Markdown(
|
| 606 |
f"""
|
| 607 |
-
# ⚔️ SWE
|
| 608 |
|
| 609 |
## 📜How It Works
|
| 610 |
- **Blind Comparison**: Submit a SE-related query to two anonymous FMs randomly selected from up to {len(available_models)} top models from OpenAI, Gemini, Grok, Claude, Deepseek, Qwen, Llama, Mistral, and others.
|
|
|
|
| 561 |
leaderboard_intro = gr.Markdown(
|
| 562 |
"""
|
| 563 |
# 🏆 FM4SE Leaderboard: Community-Driven Evaluation of Top Foundation Models (FMs) in Software Engineering (SE) Tasks
|
| 564 |
+
The SWE-Arena is an open-source platform designed to evaluate foundation models through human preference, fostering transparency and collaboration. This platform aims to empower the SE community to assess and compare the performance of leading FMs in related tasks. For technical details, check out our [paper](https://arxiv.org/abs/2502.01860).
|
| 565 |
""",
|
| 566 |
elem_classes="leaderboard-intro",
|
| 567 |
)
|
|
|
|
| 590 |
# Add a citation block in Markdown
|
| 591 |
citation_component = gr.Markdown(
|
| 592 |
"""
|
| 593 |
+
Made with ❤️ for SWE-Arena. If this work is useful to you, please consider citing:
|
| 594 |
```
|
| 595 |
@inproceedings{zhao2025se,
|
| 596 |
+
title={SWE-Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering},
|
| 597 |
author={Zhao, Zhimin},
|
| 598 |
booktitle={ACM international conference on AI Foundation Models and Software Engineering},
|
| 599 |
year={2025}}
|
|
|
|
| 604 |
# Add title and description as a Markdown component
|
| 605 |
arena_intro = gr.Markdown(
|
| 606 |
f"""
|
| 607 |
+
# ⚔️ SWE-Arena: Explore and Test Top FMs with SE Tasks by Community Voting
|
| 608 |
|
| 609 |
## 📜How It Works
|
| 610 |
- **Blind Comparison**: Submit a SE-related query to two anonymous FMs randomly selected from up to {len(available_models)} top models from OpenAI, Gemini, Grok, Claude, Deepseek, Qwen, Llama, Mistral, and others.
|