Compression level 9

Benchmark index · Median overview · ← Level 8 · Level 10 →

Recorded run: long-20261109 (2026-11-09). Raw results · Environment · Run analysis.

Median across all datasets

Each of the 8 datasets has equal weight, including empty and tiny input. Speed / C = C mean latency / implementation mean latency; output / C = implementation bytes / C bytes. We take the median of these 8 per-dataset ratios separately for speed and size. 1× matches C; higher speed and lower output are better. These are medians across datasets, not median sample latencies, and do not imply statistical significance.

Median speed and output relative to C at level 9

Implementation	Median speed / C ↑	Median output / C ↓	Datasets
zstd C	1.000×	1.000×	8
mzstd	1.266×	1.000×	8

Measurement setup and interpretation

zstd 1.5.7 (the C library built by zstd-ffi) and mzstd at the recorded working tree compress identical bytes at this level. Every frame was checked byte-identical to zstd’s and decoded back to its input before any timing.

These are cold native API measurements: construction, allocation, compression, and disposal. Complete known input; 50 samples, 3 s warmup, at least 6 s measurement. Host: AMD Ryzen 9 7950X, Linux KVM guest with two vCPUs: the encoder suite, then the decoder suite, each in one Criterion process pinned to vCPU 1; nothing else ran in the guest. Other tenants loaded the host: a fixed C decode varied by 8-43% (p10-p90 wall time) through the day, so sampling was lengthened to average over the noise. unset; Cargo release defaults (bench profile), runtime SIMD dispatch (AVX-512 level on this host; the decoder runs its block loops at the AVX2 level).

Chart whiskers and table intervals describe 95% confidence bounds on mean timing. They do not capture all host or allocator variation. Throughput bounds are transformed latency bounds. Output / input is compressed bytes divided by input bytes; smaller is better, and values above 100% mean expansion. For empty input, throughput and output / input are undefined (—). See the run analysis for measurement limitations.

Dataset details

Ordered by mzstd speed / C, highest first; all 8 datasets are shown. This order uses recorded mean latency, not statistical significance. Bars start at zero.

empty · tiny-text · repeated-1m · binary-64k · random-64k · random-1m · text-1m · alice29

empty

Empty input; measures API overhead. Input: 0 bytes.

mzstd speed / C: 10.021×; output: 9 / 9 bytes.

Level 9: empty speed and compressed size

Exact measurements and confidence bounds

Implementation	Mean, ns	95% mean interval, ns	MiB/s	Output bytes	Output / input	Speed / C
zstd C	2,274	2,221–2,335	—	9	—	1.000×
mzstd	226.9	221.9–232.8	—	9	—	10.021×

tiny-text

44-byte quick-brown-fox sentence. Input: 44 bytes.

mzstd speed / C: 5.109×; output: 53 / 53 bytes.

Level 9: tiny-text speed and compressed size

Exact measurements and confidence bounds

Implementation	Mean, µs	95% mean interval, µs	MiB/s	Output bytes	Output / input	Speed / C
zstd C	2.623	2.574–2.68	16.00	53	120.455%	1.000×
mzstd	0.5134	0.4936–0.536	81.73	53	120.455%	5.109×

repeated-1m

1 MiB of repeated a bytes. Input: 1,048,576 bytes.

mzstd speed / C: 2.345×; output: 49 / 49 bytes.

Level 9: repeated-1m speed and compressed size

Exact measurements and confidence bounds

Implementation	Mean, µs	95% mean interval, µs	MiB/s	Output bytes	Output / input	Speed / C
zstd C	622.8	603.3–646.9	1,605.73	49	0.005%	1.000×
mzstd	265.6	262.6–269.2	3,765.15	49	0.005%	2.345×

binary-64k

64 KiB of structured binary bytes: ((i / 16) XOR i) modulo 256. Input: 65,536 bytes.

mzstd speed / C: 1.279×; output: 1,270 / 1,270 bytes.

Level 9: binary-64k speed and compressed size

Exact measurements and confidence bounds

Implementation	Mean, µs	95% mean interval, µs	MiB/s	Output bytes	Output / input	Speed / C
zstd C	33.94	33.52–34.43	1,841.47	1,270	1.938%	1.000×
mzstd	26.53	25.41–27.8	2,355.46	1,270	1.938%	1.279×

random-64k

64 KiB prefix of the deterministic pseudorandom corpus. Input: 65,536 bytes.

mzstd speed / C: 1.253×; output: 65,546 / 65,546 bytes.

Level 9: random-64k speed and compressed size

Exact measurements and confidence bounds

Implementation	Mean, µs	95% mean interval, µs	MiB/s	Output bytes	Output / input	Speed / C
zstd C	29.45	28.34–30.6	2,122.31	65,546	100.015%	1.000×
mzstd	23.5	22.92–24.16	2,659.48	65,546	100.015%	1.253×

random-1m

1 MiB of deterministic xorshift64 pseudorandom bytes. Input: 1,048,576 bytes.

mzstd speed / C: 1.102×; output: 1,048,609 / 1,048,609 bytes.

Level 9: random-1m speed and compressed size

Exact measurements and confidence bounds

Implementation	Mean, µs	95% mean interval, µs	MiB/s	Output bytes	Output / input	Speed / C
zstd C	529.5	515–543.5	1,888.72	1,048,609	100.003%	1.000×
mzstd	480.3	464.3–496	2,081.86	1,048,609	100.003%	1.102×

text-1m

Alice text repeated cyclically to 1 MiB. Input: 1,048,576 bytes.

mzstd speed / C: 1.090×; output: 52,381 / 52,381 bytes.

Level 9: text-1m speed and compressed size

Exact measurements and confidence bounds

Implementation	Mean, µs	95% mean interval, µs	MiB/s	Output bytes	Output / input	Speed / C
zstd C	3,047	2,932–3,166	328.23	52,381	4.995%	1.000×
mzstd	2,795	2,694–2,898	357.78	52,381	4.995%	1.090×

alice29

Alice in Wonderland text from the Canterbury corpus (testdata/alice29.txt). Input: 152,089 bytes.

mzstd speed / C: 1.006×; output: 52,188 / 52,188 bytes.

Level 9: alice29 speed and compressed size

Exact measurements and confidence bounds

Implementation	Mean, µs	95% mean interval, µs	MiB/s	Output bytes	Output / input	Speed / C
zstd C	2,672	2,623–2,729	54.29	52,188	34.314%	1.000×
mzstd	2,657	2,617–2,702	54.60	52,188	34.314%	1.006×

Keyboard shortcuts

mzstd