Compression level 18
Benchmark index · Median overview · ← Level 17 · Level 19 →
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 | 1.287× | 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 · random-1m · repeated-1m · binary-64k · text-1m · alice29 · random-64k
empty
Empty input; measures API overhead. Input: 0 bytes.
mzstd speed / C: 6.005×; 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 | 2,481 | 2,380–2,592 | — | 9 | — | 1.000× |
| mzstd | 413.1 | 397.5–430.4 | — | 9 | — | 6.005× |
tiny-text
44-byte quick-brown-fox sentence. Input: 44 bytes.
mzstd speed / C: 1.502×; 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 | 6.955 | 6.838–7.088 | 6.03 | 53 | 120.455% | 1.000× |
| mzstd | 4.632 | 4.475–4.812 | 9.06 | 53 | 120.455% | 1.502× |
random-1m
1 MiB of deterministic xorshift64 pseudorandom bytes. Input: 1,048,576 bytes.
mzstd speed / C: 1.401×; 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 | 6.256e+04 | 5.65e+04–6.863e+04 | 15.98 | 1,048,609 | 100.003% | 1.000× |
| mzstd | 4.466e+04 | 4.295e+04–4.635e+04 | 22.39 | 1,048,609 | 100.003% | 1.401× |
repeated-1m
1 MiB of repeated a bytes. Input: 1,048,576 bytes.
mzstd speed / C: 1.367×; 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 | 851.6 | 826.8–877.8 | 1,174.21 | 49 | 0.005% | 1.000× |
| mzstd | 623.1 | 607.9–640 | 1,604.80 | 49 | 0.005% | 1.367× |
binary-64k
64 KiB of structured binary bytes: ((i / 16) XOR i) modulo 256. Input: 65,536 bytes.
mzstd speed / C: 1.207×; 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 | 151.3 | 146.7–156.8 | 413.01 | 1,259 | 1.921% | 1.000× |
| mzstd | 125.4 | 121.5–129.8 | 498.46 | 1,259 | 1.921% | 1.207× |
text-1m
Alice text repeated cyclically to 1 MiB. Input: 1,048,576 bytes.
mzstd speed / C: 1.127×; output: 49,433 / 49,433 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, µs | 95% mean interval, µs | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 1.691e+04 | 1.648e+04–1.739e+04 | 59.12 | 49,433 | 4.714% | 1.000× |
| mzstd | 1.501e+04 | 1.464e+04–1.544e+04 | 66.63 | 49,433 | 4.714% | 1.127× |
alice29
Alice in Wonderland text from the Canterbury corpus (testdata/alice29.txt). Input: 152,089 bytes.
mzstd speed / C: 1.054×; output: 49,215 / 49,215 bytes.
Exact measurements and confidence bounds
| Implementation | Mean, µs | 95% mean interval, µs | MiB/s | Output bytes | Output / input | Speed / C |
|---|---|---|---|---|---|---|
| zstd C | 3.018e+04 | 2.912e+04–3.127e+04 | 4.81 | 49,215 | 32.359% | 1.000× |
| mzstd | 2.864e+04 | 2.757e+04–2.972e+04 | 5.06 | 49,215 | 32.359% | 1.054× |
random-64k
64 KiB prefix of the deterministic pseudorandom corpus. Input: 65,536 bytes.
mzstd speed / C: 1.034×; 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 | 1,136 | 1,117–1,158 | 55.00 | 65,546 | 100.015% | 1.000× |
| mzstd | 1,099 | 1,062–1,143 | 56.85 | 65,546 | 100.015% | 1.034× |