Parsimony
an open-source benchmark for how much code AI models add
Get picks like this daily. The day's top launches, AI/tech news, and a weekly opportunity spotlight — straight to your inbox.
This is 1 of 71 launches in llm benchmarking tools — see how it stacks up on momentum and crowding →
179 other launches read as similar to this one →
Details
- External ID
- 50077619
- Source
- HN
- Company
- —
- Product
- Parsimony
- Website domain
- lasu.dev
- Launched
- Oct. 13, 2026
- Cohort
- —
- Upvotes
- 41
- Upvotes percentile
- 0.78
- Tags
- —
Description
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. I wanted to measure this since it matters most for long-term projects.Method: it takes the patches that benchmarks already publish (DeepSWE, SWE-bench Verified, SWE-bench Live) and counts "coding units": syntax elements like statements, calls, names and literals. I didn't use lines of code, so cramming code isn't rewarded. Deleted code is subtracted, so it measures net units.GPT-6 and Claude 5.5 have no public patches yet, so I ran them myself on 3–10 tasks on my own subscriptions (shown as faded circles, not ranked).Any feedback or model contributions are welcome, especially public patch exports for newer models.GitHub: https://github.com/La5u/ParsimonyNot affiliated with any of the benchmarks.
Enrichment
- Niche
- llm benchmarking tools
- Vertical
- Horizontal
- Function
- Observability & eval
- Audience
- Developer
- AI stance
- AI-native
- Project type
- Hobby / open-source project
- Normalized one-liner
- code bloat benchmark for ai models
- Manually corrected
- False
Discussion
4 comments analyzed.
Competitors mentioned: Astra, Claude
Concerns raised: Astra generates unreadably terse code, Claude generates overly verbose code and tests
Feature requests: Methods to reduce generated code complexity and verbosity
Competitors
Other products that read as similar to this one — 179 launches clear the similarity bar, closest 8 shown.
Attention rank: #38 of 180 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 343 days after the earliest competitor.
- Cheddar-bench · hn · 2026-02-22 · 9 upvotes · similarity 0.51
- Benchmark: AI doesn't find bugs unless you tell it what's wrong · hn · 2026-10-01 · 5 upvotes · similarity 0.47
- We scored 50k PRs with AI · hn · 2026-03-30 · 11 upvotes · similarity 0.46
- Open Benchmarks Grants– a $3M commitment to close the AI eval gap · hn · 2026-02-11 · 6 upvotes · similarity 0.45
- Benchmark your team's AI coding security posture · hn · 2025-11-05 · 5 upvotes · similarity 0.45
- occam · github · 2026-09-27 · 12 upvotes · similarity 0.45
- Topos · hn · 2026-06-25 · 5 upvotes · similarity 0.45
- Deeds · github · 2026-10-04 · 19 upvotes · similarity 0.43
Other launches for this product
- No other launches for this product.