Skip to content

Commit ca4b16c

Browse files
Add scenario browser functionality with new HTML and TypeScript files. Update package.json to include a script for rebuilding scenario annotations. Enhance demo layout with a new scenarios page and associated styles for improved user experience.
1 parent 43038d6 commit ca4b16c

91 files changed

Lines changed: 28273 additions & 5369 deletions

File tree

Some content is hidden

Large Commits have some content hidden by default. Use the searchbox below for content that may be hidden.

demo/index.html

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -37,6 +37,7 @@
3737
</a>
3838
<nav class="header-nav">
3939
<a href="#demo">Live Demo</a>
40+
<a href="./scenarios.html">Scenarios</a>
4041
<a href="#eval-results">Results</a>
4142
<a href="https://doi.org/10.5281/zenodo.20434088" target="_blank" rel="noreferrer">Dataset ↗</a>
4243
<a href="https://notebooklm.google.com/notebook/aa9fa965-4a1b-400d-a605-37f0632c2738" target="_blank" rel="noreferrer">NotebookLM ↗</a>
@@ -413,9 +414,10 @@ <h3 class="share-card__title">📦 Official evaluation dataset</h3>
413414
</p>
414415
</div>
415416
<div class="share-card__actions">
417+
<a href="./scenarios.html" class="btn btn-primary">Browse scenarios</a>
416418
<a
417419
href="https://doi.org/10.5281/zenodo.20434088"
418-
class="btn btn-primary"
420+
class="btn btn-ghost"
419421
target="_blank"
420422
rel="noreferrer"
421423
>View on Zenodo ↗</a>

demo/public/eval-multistep-report-gemini35flash.json

Lines changed: 3350 additions & 0 deletions
Large diffs are not rendered by default.

demo/public/eval-multistep-report-gpt5.json

Lines changed: 3361 additions & 0 deletions
Large diffs are not rendered by default.

demo/public/eval-multistep-report-gpt5nano.json

Lines changed: 3401 additions & 0 deletions
Large diffs are not rendered by default.

demo/public/eval-multistep-report-llama318B.json

Lines changed: 3410 additions & 0 deletions
Large diffs are not rendered by default.

demo/public/eval-multistep-report-qwen-gptoss.json

Lines changed: 6804 additions & 0 deletions
Large diffs are not rendered by default.

demo/public/eval-multistep-report.json

Lines changed: 0 additions & 90 deletions
This file was deleted.

0 commit comments

Comments
 (0)