Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/ChenWu98/agent-attack
/ eval_step.py
File
eval_step.py
scripts/eval_step.py:None–None ·
view source on GitHub ↗
Source
from the content-addressed store, hash-verified
1
""
"Script to run single-step evaluation on the benchmark.
2
3
Modified
from
https://github.com/web-arena-x/webarena/blob/main/run.py.
4
""
"
Callers
nothing calls this directly
Calls
7
get_examples
Function · 0.90
init
Method · 0.80
config
Function · 0.70
prepare
Function · 0.70
dump_config
Function · 0.70
run
Function · 0.70
eval_from_file
Function · 0.70
Tested by
no test coverage detected