Compression level 16
Benchmark index · Median overview · ← Level 15 · Level 17 →
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.
| Implementation | Median speed / C ↑ | Median output / C ↓ | Datasets |
|---|---|---|---|
| zstd C | 1.000× | 1.000× | 8 |
| mzstd | 1.337× | 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 · random-1m · repeated-1m · tiny-text · text-1m · binary-64k · random-64k · alice29
empty
Empty input; measures API overhead. Input: 0 bytes.
mzstd speed / C: 6.648×; output: 9 / 9 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, ns | 95% mean interval, ns | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 2,399 | 2,313–2,493 | — | 9 | — | 1.000× |
| mzstd | 360.9 | 347.3–376.2 | — | 9 | — | 6.648× |
random-1m
1 MiB of deterministic xorshift64 pseudorandom bytes. Input: 1,048,576 bytes.
mzstd speed / C: 1.672×; output: 1,048,609 / 1,048,609 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, µs | 95% mean interval, µs | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 5.585e+04 | 5.078e+04–6.109e+04 | 17.90 | 1,048,609 | 100.003% | 1.000× |
| mzstd | 3.34e+04 | 3.171e+04–3.518e+04 | 29.94 | 1,048,609 | 100.003% | 1.672× |
repeated-1m
1 MiB of repeated a bytes. Input: 1,048,576 bytes.
mzstd speed / C: 1.369×; output: 49 / 49 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, µs | 95% mean interval, µs | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 891.5 | 855.5–929.5 | 1,121.74 | 49 | 0.005% | 1.000× |
| mzstd | 651 | 629.4–673.7 | 1,536.19 | 49 | 0.005% | 1.369× |
tiny-text
44-byte quick-brown-fox sentence. Input: 44 bytes.
mzstd speed / C: 1.347×; output: 53 / 53 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, µs | 95% mean interval, µs | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 6.873 | 6.804–6.963 | 6.11 | 53 | 120.455% | 1.000× |
| mzstd | 5.102 | 4.897–5.318 | 8.22 | 53 | 120.455% | 1.347× |
text-1m
Alice text repeated cyclically to 1 MiB. Input: 1,048,576 bytes.
mzstd speed / C: 1.328×; output: 49,924 / 49,924 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, µs | 95% mean interval, µs | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 1.399e+04 | 1.361e+04–1.436e+04 | 71.49 | 49,924 | 4.761% | 1.000× |
| mzstd | 1.053e+04 | 1.021e+04–1.089e+04 | 94.94 | 49,924 | 4.761% | 1.328× |
binary-64k
64 KiB of structured binary bytes: ((i / 16) XOR i) modulo 256. Input: 65,536 bytes.
mzstd speed / C: 1.242×; output: 1,259 / 1,259 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, µs | 95% mean interval, µs | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 147.9 | 144.9–152.1 | 422.49 | 1,259 | 1.921% | 1.000× |
| mzstd | 119.1 | 117.6–121.1 | 524.55 | 1,259 | 1.921% | 1.242× |
random-64k
64 KiB prefix of the deterministic pseudorandom corpus. Input: 65,536 bytes.
mzstd speed / C: 1.149×; output: 65,546 / 65,546 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, µs | 95% mean interval, µs | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 1,206 | 1,165–1,251 | 51.84 | 65,546 | 100.015% | 1.000× |
| mzstd | 1,049 | 1,026–1,079 | 59.57 | 65,546 | 100.015% | 1.149× |
alice29
Alice in Wonderland text from the Canterbury corpus (testdata/alice29.txt). Input: 152,089 bytes.
mzstd speed / C: 1.009×; output: 49,355 / 49,355 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, µs | 95% mean interval, µs | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 1.663e+04 | 1.621e+04–1.707e+04 | 8.72 | 49,355 | 32.451% | 1.000× |
| mzstd | 1.649e+04 | 1.583e+04–1.712e+04 | 8.80 | 49,355 | 32.451% | 1.009× |