Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/Alibaba-NLP/DeepResearch
/ evaluate.py
File
evaluate.py
WebAgent/WebResummer/src/evaluate.py:None–None ·
view source on GitHub ↗
Source
from the content-addressed store, hash-verified
1
import
argparse
2
from
concurrent.futures
import
ThreadPoolExecutor, as_completed
3
from
judge_prompt
import
JUDGE_PROMPT_GAIA, JUDGE_PROMPT_BC_en, JUDGE_PROMPT_BC_zh
4
import
os
Callers
nothing calls this directly
Calls
4
process_one_prediction
Function · 0.85
parse_args
Method · 0.80
single_round_statistics
Function · 0.70
get
Method · 0.45
Tested by
no test coverage detected