Mdarena
Benchmark your Claude.md against your own PRs
Details
- External ID
- 47655078
- Source
- HN
- Company
- —
- Product
- Mdarena
- Website domain
- github.com
- Launched
- April 5, 2026
- Cohort
- —
- Upvotes
- 22
- Upvotes percentile
- 0.7647814910025706
- Tags
- —
- Fetched at
- Sept. 7, 2026, 9:26 p.m.
- Updated at
- Sept. 7, 2026, 9:26 p.m.
Enrichment
- Theme
- ML inference and model optimization
- Vertical
- Horizontal
- Function
- Analytics & BI
- Audience
- Developer
- AI stance
- AI feature
- Project type
- Hobby / open-source project
- Normalized one-liner
- benchmark ai-generated code against pull requests
- Manually corrected
- False
Could you build this?
Yes This is a benchmarking CLI/web utility that reads past PR diffs via the GitHub API, feeds them into an LLM along with instructions (Claude.md), and compares the output against actual PR changes.
Discussion
4 comments analyzed.
Competitors mentioned: LynxPrompt
Concerns raised: contradictory research on claude.md effectiveness, unclear if system prompts actually improve performance
Feature requests: continuous monitoring as codebase changes
Competitors
Other products that read as similar to this one — 451 launches clear the similarity bar, closest 8 shown.
Attention rank: #112 of 452 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).
Launched 156 days after the earliest competitor.
- harness-perf-benchmark · github · 2026-09-19 · 23 upvotes · similarity 0.47
- Kerf-CLI · hn · 2026-04-08 · 9 upvotes · similarity 0.46
- Captain - The Reliable Alternative to RAG · yc · 2025-11-07 · 115 upvotes · similarity 0.45
- Viveka: filter LLM output against a Lean-verified Advaita Vedanta model · hn · 2026-06-02 · 7 upvotes · similarity 0.45
- Claude Reflect · hn · 2026-01-04 · 75 upvotes · similarity 0.44
- Stratum · hn · 2026-03-12 · 12 upvotes · similarity 0.44
- Pgcraft · hn · 2026-05-26 · 6 upvotes · similarity 0.44
- claude-reverse-proxy · github · 2026-09-18 · 11 upvotes · similarity 0.44
Other launches for this product
- No other launches for this product.
Same idea, different domain
Nobody's really built a analytics & bi tool for Legal yet.