Measured - byte-exact - 2026

Pedulli vs LZO

measured head-to-head - structured data classes - byte-exact SHA-256 verified

TL;DR - honest
LZO is real-time / embedded-grade - RAM compression in btrfs, OpenVPN, RAID-Z. Pedulli is a best-of-N racer - it races xz, zstd, brotli and your data's SRD math and keeps the smallest byte-exact output, so it is never larger than the best standard codec (worst case +1 byte). It wins ratio outright across structured classes and ties the best codec on already-optimal/random data; LZO wins only on hard real-time guarantees and embedded-board availability, not on output size.

The measured table

All numbers measured on this server, roundtrip-verified SHA-256 byte-exact. Proofs available on request.

Input	LZO 1x	Pedulli (best-of-N)	Δ
1 MiB of zeros	4,210 B	13 B	much smaller (redundant input)
JSON 31 KB	7,512 B	1,265 B	-83%
HTML 161 KB	72,108 B	38,757 B	-46.3%
Apache logs 3.5 MB	518 KB	217 KB	-58.1%
MP4 master 10 MB	10,201,438 B	9,430,108 B	-771 KB
Random bytes 1 MB	1,048,609 B (+33 B)	1,048,577 B (+1 B)	32 B less overhead

What LZO does better (honest)

Real-time guarantees. Worst-case bounded - used in kernel data paths.
Tiny memory footprint. Runs on embedded boards with kilobytes of RAM.
BSD/GPL license, battle-tested since 1996.

What Pedulli does that LZO does not

+1 byte never-worse floor vs LZO's +33 on random data.
Best-of-N racing. Races xz, zstd, brotli and your data's SRD math, keeps the smallest verified output - never larger than the best standard codec, far tighter on every structured class measured.
GDPR-compliant web service + API.
Zero data retention, EU-sovereign.

When to use which

Use LZO for kernel-data-path compression, embedded firmware and hard real-time pipelines. Use Pedulli when ratio matters and you can afford a service call or API process - plus the per-file +1 byte never-worse floor.

Run the free trial Pricing / API All benchmarks

More comparisons: lzop - lz4 - Snappy - LZFSE