Spaces:

openenvarena
/

arena

Running on CPU Upgrade

App Files Files Community

arena

43.6 MB

Ctrl+K

5 contributors

History: 38 commits

xdotli

Restyle in the PostTrain Arena brand, with fixes from worst-case testing and dogfooding

e40d6dc verified 21 days ago

.gitattributes

1.69 kB
feat: about arena (#4) 23 days ago
AGENTS.md

21.2 kB
Restyle in the PostTrain Arena brand, with fixes from worst-case testing and dogfooding 21 days ago
Dockerfile

261 Bytes
OpenEnv Arena: one-page submission portal 24 days ago
README.md

3.78 kB
Credit BenchFlow and PostTrain Arena on the page (#14) 21 days ago
app.py

2.65 kB
Credit BenchFlow and PostTrain Arena on the page (#14) 21 days ago
arena_bridge.py

12.1 kB
The public site talks only to the production Arena 22 days ago
auth.py

7.57 kB
Sign-in, messages, your submissions and a tasks-vs-score chart 24 days ago
benchflow.svg

8.37 kB
Credit BenchFlow and PostTrain Arena on the page (#14) 21 days ago
hero.jpg

228 kB
xet

Open Env Arena 24 days ago
icon.svg

2.77 kB
Open Env Arena 24 days ago
index.html

70.2 kB
Restyle in the PostTrain Arena brand, with fixes from worst-case testing and dogfooding 21 days ago
leaderboard.json

1.9 kB
Revert the baseline and model-text changes since e08a03d; baseline is the untrained Qwen3.8-27B 22 days ago
nebius.svg

2.57 kB
fix: arena dashboard (#5) 23 days ago
open-env-arena-launch.mp4

43.1 MB
xet

fix: refresh arena launch page 22 days ago
test_app.py

26.7 kB
Restyle in the PostTrain Arena brand, with fixes from worst-case testing and dogfooding 21 days ago
test_leaderboard.cjs

19.6 kB
Restyle in the PostTrain Arena brand, with fixes from worst-case testing and dogfooding 21 days ago
test_leaderboard_api.py

6.07 kB
Revert the baseline and model-text changes since e08a03d; baseline is the untrained Qwen3.8-27B 22 days ago
test_messages.cjs

6.2 kB
Restyle in the PostTrain Arena brand, with fixes from worst-case testing and dogfooding 21 days ago
test_run_alerts.cjs

3.46 kB
Restyle in the PostTrain Arena brand, with fixes from worst-case testing and dogfooding 21 days ago