ToolQA
ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.
night-chen/ToolQA
View on GitHub ↗ToolQA, a new dataset to evaluate the capabilities of LLMs in answering challenging questions with external tools. It offers two levels (easy/hard) across eight real-life scenarios.
ToolQA grew -0.3% in the last 30 days, ranks 35th of 67 in Dataset Collections, last commit 1,163 days ago.
Star trajectory
115 days tracked-0.3% in 30d, below the Dataset Collections median of +0.5%.
Last commit 1,163 days ago, staler than the median of 177d.
How it compares in Dataset Collections
Ranked 35th of 67 by stars.
- Language
- Jupyter Notebook
- License
- Apache License 2.0
- Contributors
- 2
- Forks
- 12
- Watchers
- 4
- Open issues
- 5
- Releases
- 0
- Created
- 2023-06-06
- Stars this week
- +0
You've seen where ToolQA stands today.
Get the moves before everyone else: the 5 Dataset Collections repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.