Sep 15 07:31 Archive Sol and Opus baseline and DeepAgents evaluation results Add results/<model>/<baseline|deepagents>/ with per-task JSONL/CSV, summaries and configuration. Four groups of 1,000 tasks; no date directories.
Preserve historical amended-comparison provenance and unknown states. This is result storage only: leave the displayed leaderboard results.csv and all existing site files unchanged. Sep 4 06:54 Update index.html 06:52 Update results.csv 06:51 Update results.csv 06:49 Update results.csv 06:33 Update results.csv Aug 25 03:00 Update index.html Aug 24 03:41 Update index.html Aug 23 02:51 Update index.html 02:45 Update results.csv 02:23 Update index.html Aug 19 13:25 Update index.html 13:20 Update index.html 13:17 Update index.html 13:12 Update index.html 13:05 Update index.html 12:50 Update index.html 10:09 Update results.csv 09:59 Update results.csv 08:04 Update index.html Aug 17 15:09 Update results.csv 14:39 Update index.html 14:27 Update index.html 14:22 Update index.html 14:22 Update index.html 14:21 Update index.html 14:20 Update index.html 14:19 Delete app.py 13:52 Create app.py 13:51 Create requirements.txt 13:19 Update index.html 13:18 Create results.csv 13:14 Update index.html 09:28 Update index.html 06:42 Update index.html 06:37 initial commit 06:37 Duplicate from gradio/gradio-lite-template zsss0316 +1: Xenova Co-authored-by: Joshua <Xenova@users.noreply.huggingface.co>