OmniCode is a new benchmark with 1794 manually validated tasks across four software engineering categories and three languages, revealing that agents like SWE-Agent perform poorly on test generation especially in C++ and Java.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
OmniCode: A Benchmark for Evaluating Software Engineering Agents
OmniCode is a new benchmark with 1794 manually validated tasks across four software engineering categories and three languages, revealing that agents like SWE-Agent perform poorly on test generation especially in C++ and Java.