Skip to content
Bluzen Labs
All projects
EvaluationActive

LumenEval

Benchmarks with their failure cases attached

An evaluation harness that refuses to emit a single number without the error analysis that explains it.

Category
Evaluation
Status
Active
Language
Python
Licence
Apache-2.0
Stars
640
Since
2026

A leaderboard without error analysis is marketing. LumenEval is the harness we built after publishing one number we could not defend in the follow-up thread.

What a run emits

  • Aggregate metrics, stratified by whatever axes the task declares.
  • The worst hundred cases, rendered.
  • The exact config, dataset revision and model revision, hashed together.

Status

Active, and used for every number this site publishes.

Writing

Research28 Aug 2026 · 7 min

The tail is the product

Why we throw away aggregate F1 on tagging benchmarks, and what we report instead. A short argument with a long table attached.

Ashish Kumar, Rin AmagaiRead

Related projects

Aurora Corpus

The dataset everything else is trained on

Active

An 18M-image illustration corpus with tags, captions and quality bands, plus the whole filtering pipeline that produced it.

#Data#Ray#Pipelines
Language
Python
Stars
980
Licence
CC-BY-4.0
Category
Data

BluzenTagger

Multi-label tagging for illustration

Active

A tagger over a 12k-tag vocabulary that holds up on the long tail, where general-purpose vision models quietly collapse into the fifty most common labels.

#PyTorch#ONNX#Vision#Tagging
Language
Python
Stars
1.4k
Licence
Apache-2.0
Category
Research

MochiCore

Adapter training that fits on one GPU

Stable

The trainer the rest of the lab runs on. Adapter families, quantised paths and a config format you can read out loud.

#PyTorch#LoRA#Training
Language
Python
Stars
3.6k
Licence
MIT
Category
Training