Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.
Tyson and others , title =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rethinking Code Performance Benchmarks for LLMs
Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.