An in-IDE pairwise-preference platform for code LLMs reveals that real developer choices rank models differently than static coding benchmarks.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Copilot Arena: A Platform for Code LLM Evaluation in the Wild
An in-IDE pairwise-preference platform for code LLMs reveals that real developer choices rank models differently than static coding benchmarks.