CodeFlowBench is a new benchmark with 5000+ problems and GitHub-sourced repos that evaluates LLMs on multi-turn code reuse using dependency-tree structural metrics, revealing performance drops as complexity rises.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
CodeFlowBench: A Multi-turn, Iterative Benchmark for Complex Code Generation
CodeFlowBench is a new benchmark with 5000+ problems and GitHub-sourced repos that evaluates LLMs on multi-turn code reuse using dependency-tree structural metrics, revealing performance drops as complexity rises.