cd/entity/Large Text Compression Benchmark· home› entities› Large Text Compression Benchmark

grep -l @large text compression benchmark /news/*.json | wc -l → 1

Large Text Compression Benchmark

mentions 1 type Person feed RSS

// recent coverage 1 mentions

05:50

2026-09-08

mattmahoney.net

artificial-intelligence

Fx2-Cmix-Transformer

The fx2-cmix-transformer program achieved the top ranking on the Large Text Compression Benchmark, compressing the first 10^9 bytes of the English Wikipedia XML dump (enwik9) to 96,996,198 bytes, with…

// co-occurs with top 3 entities

Matt Mahoney 1 fx2-cmix-transformer 1 Wikipedia 1

// topics top 2 topics

artificial intelligence 1 natural language processing 1