openhands commited on
Commit
7abbbe1
·
1 Parent(s): c52135c

Update intro paragraph with new content

Browse files

- Remove pre-release notice
- Add link to OpenHands Software Agent SDK
- Minor wording improvements

Files changed (1) hide show
  1. content.py +3 -5
content.py CHANGED
@@ -17,17 +17,15 @@ TITLE = """<h1 align="left" id="space-title">OpenHands Index</h1>"""
17
 
18
  INTRO_PARAGRAPH = """
19
  <p>
20
- <b>Pre-release:</b> this codebase is not yet released.
21
  </p>
22
 
23
- <p>
24
- <strong>OpenHands Index</strong> is a comprehensive benchmark for evaluating AI coding agents across real-world software engineering tasks. As agents become more capable, we need standardized ways to measure their performance across diverse challenges—from fixing bugs to building applications.
25
- </p>
26
 
27
  <p>
28
- Our index aggregates results from multiple benchmarks spanning five categories: <strong>Issue Resolution</strong> (fixing bugs), <strong>Greenfield</strong> (building new apps), <strong>Frontend</strong> (UI development), <strong>Testing</strong> (test generation), and <strong>Information Gathering</strong>. This provides a single view of both <strong>performance</strong> and <strong>cost efficiency</strong>, enabling fair comparisons between agents.
29
  </p>
30
 
 
31
  <p>
32
  For methodology details, see the <a href="/about" class="intro-link">About</a> page.
33
  </p>
 
17
 
18
  INTRO_PARAGRAPH = """
19
  <p>
20
+ The <strong>OpenHands Index</strong> is a comprehensive benchmark for evaluating AI coding agents across real-world software engineering tasks. As agents become more capable, we need standardized ways to measure their performance across diverse challenges, from fixing bugs to building applications.
21
  </p>
22
 
 
 
 
23
 
24
  <p>
25
+ The OpenHands Index assesses models across five categories: <strong>Issue Resolution</strong> (fixing bugs), <strong>Greenfield</strong> (building new apps), <strong>Frontend</strong> (UI development), <strong>Testing</strong> (test generation), and <strong>Information Gathering</strong>. All models are currently evaluated using the <a href="https://github.com/OpenHands/software-agent-sdk">OpenHands Software Agent SDK</a>. This provides a single view of both <strong>performance</strong> and <strong>cost efficiency</strong>, enabling fair comparisons between agents.
26
  </p>
27
 
28
+
29
  <p>
30
  For methodology details, see the <a href="/about" class="intro-link">About</a> page.
31
  </p>