webarena/xiangyi-li · BenchFlow

/

mirrored 10 minutes ago

Benchmark Card Files and versions Leaderboard

Hub
Contact

0

evaluation_harness

__init__.py
181 B
evaluators.py
13.3 kB
helper_functions.py
7.57 kB

add comment

2 years ago

Shuyan ZhouUpdate README.mddaee18d

release commit

2 years ago

use fuzzy_match for UA tasks and update ua eval prompt

2 years ago