FROM THE BENCHMARK
Research notes
Our own findings from the saved runs: how the evaluation works, what related model formats mean, and what the evidence can support.
OPEN↔CLOSED
Methodology · 5 min read
One rubric for open weights and closed services
Why we re-score saved outputs instead of mixing historical and fresh quality ratings.
Read our findings12B
GGUF / MLX / CMF
Model execution · 4 min read
A different file is not always a different model
Thirteen repository entries, related weight families, and what the comparison actually measures.
Read our findings759
outputs · one quality framework
Research note · 4 min read
What we can measure before the detectors finish
The complete readability and meaning results, and the limits of a detector-free comparison.
Read our findings