SlopScupper
20 crowdincl. 3 critics

llm-eval-viewer

A lightweight web viewer for LLM evaluation results — visualize, browse and analyze evalscope outputs instantly in your browser.
Open repo on GitHub Open the demogithub.com/dynamicheart/llm-eval-viewer
JavaScript · ★ 6 · 0 forks · MIT · paperwork by the Cap'mmostly ai (inferred)light human (inferred)works-on-my-machine (inferred)other
listed 7 hours ago by dynamicheart · last checked 50 minutes ago
The owner didn't write this. This repo never submitted itself. The Cap'm found it on a truffle trawl and wrote its paperwork from what GitHub already shows. Picked by hand by the Cap'm on 2026-09-11: a lightweight browser viewer for evalscope LLM evaluation results whose README says "This project was built entirely with AI assistance". 6 stars; MIT license. The owner did not submit this. Votes count; awards don't until the owner claims it.

I'm not calling your project slop! Geeze, it's a joke... Do you own this repo?

Log in with GitHub as dynamicheart. There's no account to make: SlopScupper only asks GitHub who you are (read:user), never sees your code, and keeps just your id, login and avatar. Then you can:

  • Keep it, on your terms. Commit your own slopscore.md (spec) and press Refresh. Your paperwork replaces the Cap'm's, and you can submit it for Slop of the Day.
  • Take it down. One click on Remove. It stays gone; the trawl never brings it back.

Log in with GitHub

Can't log in as the owner? Request a takedown. No login needed, and a trawled listing comes down right away.

GitHub says
A lightweight web viewer for LLM evaluation results — visualize, browse and analyze evalscope outputs instantly in your browser.
website
https://dynamicheart.github.io/llm-eval-viewer/
topics
ai-generateddark-modeelement-plusevalscopei18njsonl-viewerllmllm-evaluationmodel-evaluationviewervisualizationvitevuevue3
created
2025-12-28 · pushed 2 weeks ago · 111 commits · 1 contributor
languages
JavaScript 53%Vue 46%CSS 1%Shell 0%HTML 0%
paperwork
licensereadme 42% health
dependencies
no dependency graph (no manifest, or disabled) · OSV.dev, checked 7 hours ago

Disclosures, inferred by the Cap'm

slopbucket
vibe-coded
category
other
ai_generated
mostly
human_touch
light
status
works-on-my-machine
language (detected)
csshtmljavascriptshellvue
topic (detected)
ai-generateddark-modeelement-plusevalscopei18njsonl-viewerllmllm-evaluationmodel-evaluationviewervisualizationvitevuevue3
license (detected)
mit

The Cap'm's log

The Cap'm wrote this paperwork, not the owner. This repo never submitted itself to SlopScore. The Cap'm picked it by hand: a lightweight browser viewer for evalscope LLM evaluation results whose README says "This project was built entirely with AI assistance". It carries the MIT license. The disclosures above are his best guess from what GitHub shows.

Is this yours? Commit a real slopscore.md and press Refresh to replace this, or remove the listing in one click. There's no account to make: you log in with GitHub.

README — the repo's own words, folded up so the grading fits on one screen

LLM Eval Viewer

中文文档

This project was built entirely with AI assistance (Claude Opus 4.6).

LLM Eval Viewer is a lightweight web tool for visualizing LLM evaluation results.
Currently supports result formats generated by evalscope.

Live Demo:
https://dynamicheart.github.io/llm-eval-viewer/

Features

  • Multi-format support: Evalscope Predictions / Reviews evaluation results
  • Directory browsing: Select a directory to auto-scan its structure, quickly switch between experiments and datasets (Chrome/Edge)
  • Statistics & distribution: Token histogram, result/finish-reason distribution, per-dataset accuracy — all interactive with click-to-filter
  • Reasoning support: Displays reasoning content marked as [R], view Text and Reasoning separately
  • Dark mode: Light / Dark / Auto theme with system preference detection
  • cURL export: Generate cURL commands from request details for quick API replay
  • i18n: English and Chinese language support

Example Files (evalscope)

You can use the following example files for local or online experience:

Screenshots

Reviews View (Dark Mode)

Reviews View - Dark Mode

Predictions View (Light Mode)

Predictions View - Light Mode

Development

cd llm-eval-viewer
npm install
npm run dev

Build

npm run build

Built with AI

This project was developed entirely through AI-assisted programming using Claude Opus 4.6. From architecture design to implementation, all code was generated and iterated via human-AI collaboration.

License

MIT

Read the rest on GitHub

Scan report · 2026-09-11
  • ✓ Prohibited terms or links
  • ✓ Repository eligibility
  • ✓ slopscore.md paperwork
  • ✓ Content policy
  • ✓ Risk review

0 comments

log in to comment.

report this listing — log in to report