CoolFace
Apppublic

open-llm-leaderboard/comparator

sourceHugging Faceupdated 2y agoView on Hugging Face
115likes
50 commits on main
19703ee2y ago

Require login for MATH Details (#3)

albertvillanova
8a914922y ago

Schedule Space restart to update list of models

albertvillanova
608184c2y ago

Support comparing environmental impact

albertvillanova
966ae7b2y ago

Fix loading message in case of timeout error

albertvillanova
dfd4a532y ago

Implement retry mechanism when HTTP timeout error

albertvillanova
719c2722y ago

Make the code robust against HTTP errors

albertvillanova
ca293bc2y ago

Delete debugging prints

albertvillanova
523fad92y ago

Support comparing model tree generations

albertvillanova
96f60e12y ago

Fix load_results for None data frames

albertvillanova
729af672y ago

Set result_paths_per_model as State

albertvillanova
e7f29e12y ago

Minor fix

albertvillanova
4a057392y ago

Improve async loading performance of Details

albertvillanova
bea70632y ago

Support more than 2 models

albertvillanova
22fb9eb2y ago

Hide MATH fewshot_config.samples with memory address

albertvillanova
31903af2y ago

Fix style

albertvillanova
b1b50fb2y ago

Add Download button

albertvillanova
9ade1c22y ago

Avoid bug with radar plot

albertvillanova
a56da8a2y ago

Plot also radar

albertvillanova
2b1d96b2y ago

Plot with plotly

albertvillanova
07db6282y ago

Plot Results

albertvillanova
ea4c6702y ago

Extract concat_results function

albertvillanova
ccc567f2y ago

Rename dataframes

albertvillanova
dcff8f72y ago

Sort 3/5/7 subtasks

albertvillanova
69bec6e2y ago

Fix missing Snark subtask

albertvillanova
7e32ac72y ago

Refactor glob to use the cache of HfFileSystem

albertvillanova
fae0e192y ago

Rename load file functions

albertvillanova
d46be0d2y ago

Fix overflow on small screens

albertvillanova
10753ac2y ago

Update README.md

albertvillanova
6411b1c2y ago

Align Details samples sorting by doc_id

albertvillanova
1d3349d2y ago

Update README.md

clefourrier
39ff1462y ago

Support loading LFS Details files

albertvillanova
148216f2y ago

Support .json and .jsonl details files

albertvillanova
e9700612y ago

Add explanation that login is required for GPQA Details

albertvillanova
41fbe9f2y ago

Change colormap to PiYG

albertvillanova
585c3fa2y ago

Rename to Hide Standard Errors

albertvillanova
581682a2y ago

Use color map for Results metrics values

albertvillanova
6cf57e42y ago

Add checkbox in Details to show only differences

albertvillanova
f12aa562y ago

Add checkbox in Configs to show only differences

albertvillanova
54e105e2y ago

Add checkbox in Results to hide stderr

albertvillanova
26ef4262y ago

Implement login for GPQA Details

albertvillanova
662ed4b2y ago

Fix loading Details with documents containing end of lines

albertvillanova
611a3ed2y ago

Fix style

albertvillanova
e3edf6d2y ago

Fix wrapping to keep non-str data

albertvillanova
19a60102y ago

Make beta-version warning less formal

albertvillanova
bd64e7a2y ago

Escape HTML tags in data

albertvillanova
76471252y ago

Fix URL to Leaderboard

albertvillanova
8f7c83f2y ago

Display loading message

albertvillanova
651545d2y ago

Add additional info to task description

albertvillanova
30a0c612y ago

Import contants as submodule

albertvillanova
b6f3b942y ago

Improve label of subtasks

albertvillanova