Fetching metadata from the HF Docker repository...
-
add complete theoremqa output for gpt-4o
-
add complete humaneval output for gpt-4o
-
add complete mmlu output for gpt-4o
-
add complete math output for gpt-4o
-
add viz tab for mint
-
add some outputs
-
update results
Xingyao Wang
-
plot success rate with cost when available
Xingyao Wang
-
add results for deepseek chat v2
Xingyao Wang
-
add codeact swe agent
Xingyao Wang
-
update gitignore
Xingyao Wang
-
add gpt4o result for 1.5
Xingyao Wang
-
move data to swe_bench_lite
Xingyao Wang
-
Merge commit 'f6d9f43457bdadd36685181efda2fd45e813a02c'
Xingyao Wang
-
visualize swe-bench-lite & fix stuck in look
Xingyao Wang
-
add cost info when exists
Xingyao Wang
-
show errrors
Xingyao Wang
-
rename dir
Xingyao Wang
-
add result for deepseek
Xingyao Wang
-
fix visualizer for json
Xingyao Wang
-
fix glob
Xingyao Wang
-
update visualizer on multi-page
Xingyao Wang
-
add results for gpt-4o
Xingyao Wang
-
change to only load merged
Xingyao Wang
-
updare resykts
Xingyao Wang
-
Update README.md
-
add absolute number of solved
Xingyao Wang
-
update float
Xingyao Wang
-
change to pct
Xingyao Wang
-
add benchmark code
Xingyao Wang
-
support multi-page
Xingyao Wang
-
also show metadata for exp results
Xingyao Wang
-
update gitignore
Xingyao Wang
-
update app
Xingyao Wang
-
support the visualization of refractored arch
Xingyao Wang
-
update gitignore
Xingyao Wang
-
remove all logs
Xingyao Wang
-
initial results
Xingyao Wang
-
initial commit