Fetching metadata from the HF Docker repository... 16 days ago
-
Add AutoBench Quality, Balanced, and Cost to the Router Benchmark board. Running
PeterKruger +1: Cursor
20 days ago
-
Point the Router Benchmark at the white paper and lock ARI at β = 0.2.
PeterKruger +1: Cursor Co-authored-by: Cursor <cursoragent@cursor.com>
24 days ago
-
Add the Router Benchmark tab and the October 2026 board.
PeterKruger +1: Cursor Router runs stay out of the model dropdown.
Co-authored-by: Cursor <cursoragent@cursor.com> -
Upload 8 files
-
Delete corpus1_2026-08-29
-
Upload 8 files
-
Upload summary_data.csv
minor fix to LM 5.1 -
Upload summary_data.csv
fix to tau bench format -
Upload summary_data.csv
fix on Gpt-5.a nomenclature -
Upload 8 files
Updated benchmark with Opus 4.7 -
Delete runs/agent1_2026-04-16
new updated version of the benchmark
-
fixed a gradio version error
-
fixed ordering of main averages
-
Upload metadata.json
-
Upload app.py
Formatting fixes for new benchmarks and some descripotions -
Upload 8 files
Adding run agentic 1
-
Upload 8 files
-
Upload 7 files
-
Update runs/run_2025-11-28/metadata.json
-
Upload 7 files
-
Delete runs/agro1_2025-12-10
-
Update runs/agro1_2025-12-10/metadata.json
-
Upload summary_data.csv
-
Upload 7 files
-
Upload 7 files
-
Update runs/run_2025-08-14/metadata.json
-
Run of November 28, 2025
-
Upload summary_data_www.csv
rounded p99 data -
Upload summary_data.csv
fixed P99 data -
Upload summary_data.csv
fixed p99 data
-
Fix short_description length in README.md for HF Spaces compatibility
-
Add multi-leaderboard support with navigation, enhanced metrics, and correlations
-
final tweaks to the text
-
minot tweaks to the text
-
optinization of the leaderboard
-
Add application code, data, requirements, and ignore venv
-
initial commit
