Parsimony
an open-source benchmark for how much code AI models add. Existing benchmarks measure solve rate and token output/cost, but don't punish excess code, which makes a codebase harder to work with in the long term.
Reactions (1)
Similar products
by description similarity
Codebased
codebased.shan AI Search Engine for Code
Sloppylint
github.comA linter for AI-generated Python code
ContextCodeCache in Rust
github.comRust Based Multi-language Static Analyser & Developer tools for the AI age.
Jolt
app.usejolt.aiAI coding tool for production, 100K+ line codebases
SeaGOAT
github.comlocal, “AI-based” grep for semantic code search