A new 303-question benchmark of realistic data science tasks finds that Claude-4-Sonnet with multi-step code generation outperforms other LLMs and agent styles, but the accuracy numbers rest on a thinly validated automatic judge.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DSBC : Data Science task Benchmarking with Context engineering
A new 303-question benchmark of realistic data science tasks finds that Claude-4-Sonnet with multi-step code generation outperforms other LLMs and agent styles, but the accuracy numbers rest on a thinly validated automatic judge.