openhands openhands commited on
Commit
369c590
·
1 Parent(s): 72b86cb

Update intro text to focus on motivation rather than metrics

Browse files

Simplified the above-the-fold description to emphasize:
- Why the index exists (need for standardized agent evaluation)
- What it provides (aggregated performance + cost view)
- Who benefits (developers and researchers)

Moved detailed metric explanations to the About page.

Co-authored-by: openhands <openhands@all-hands.dev>

Files changed (1) hide show
  1. content.py +5 -10
content.py CHANGED
@@ -21,20 +21,15 @@ INTRO_PARAGRAPH = """
21
  </p>
22
 
23
  <p>
24
- <strong>OpenHands Index</strong> provides an aggregated view of agent performance and efficiency across all benchmarks in all categories. We report:
25
  </p>
26
 
27
- <ul class="info-list">
28
- <li>
29
- <strong>Average score:</strong> A macro-average of the five category-level average scores. Each category contributes equally, regardless of how many benchmarks it includes. This ensures fair comparisons across agents with different domain strengths.
30
- </li>
31
- <li>
32
- <strong>Total cost:</strong> The sum of the agent's cost across all categories, in USD.
33
- </li>
34
- </ul>
35
 
36
  <p>
37
- This view is designed for quick comparison of general-purpose coding agents. For more details on how we calculate scores and cost, please see the <a href="/about" style="color: #6366F1; text-decoration: underline;">About</a> Page.
38
  </p>
39
  """
40
  SCATTER_DISCLAIMER = """
 
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, providing a single view of both <strong>performance</strong> and <strong>cost efficiency</strong>. This enables fair comparisons between agents, helping developers and researchers choose the right tool for their needs.
29
+ </p>
 
 
 
 
 
30
 
31
  <p>
32
+ For methodology details, see the <a href="/about" style="color: #6366F1; text-decoration: underline;">About</a> page.
33
  </p>
34
  """
35
  SCATTER_DISCLAIMER = """