git
ask
hub
Privacy
Terms
Sign in with GitHub
laugherxiao/imario-benchmark
↗
Stars ·
1
Language ·
Python
License ·
NOASSERTION
Simplify and Visualize This Repo
Scan the safety of this repo
Self Host this repo
Check out more work of Developer: laugherxiao
Ask anything about this repo to start.
Clone this repo and walk me through running score.py to reproduce the published accuracy numbers.
Explain the difference between the raw 1-TV and 1-MAE accuracy metrics used in this benchmark.
Help me understand what the novel, trend, and covered question tiers mean in this benchmark.
Show me how to rebuild the Pew Research question bank using the extraction scripts in data/extraction.
Explain what evidence in verification/ makes this benchmark's numbers hard to fake.
Full explanation on explaingit →
📎
Send
By chatting or signing in you agree to the
Terms
and chat-message logging (revocable in
History
).