Performance of WebAssembly runtimes in 2026 - Frank DENIS random thoughts.
Skip to main content
I wanted to know if WebAssembly runtimes are getting faster.
This is a follow-up to the earlier libsodium WebAssembly benchmarks from 2019, 2021 and 2023.
Not “does the newest version beat native code in one microbenchmark?”, and not “which runtime has the prettiest benchmark chart?”, but something more boring and more useful:
If I take the same C crypto code, compile it to WebAssembly, and run it on the latest runtime, a runtime from one year ago, and a runtime from two years ago, are things actually improving?
So I benchmarked libsodium on WebAssembly runtimes released around June 2024, June 2025, and June 2026.
The short version:
WAVM and WasmEdge can be very fast, but I only got a complete 2026 WAVM run, and the latest stable WasmEdge release was unusably slow on this benchmark on my machine.
wasm2c, Wasmer, and Wasmtime are all close enough to native to be interesting for CPU-bound crypto.
Wazero is slower, but stable.
Node is still much slower than native for this kind of WASI workload.
Bun got dramatically faster since last year, but is still behind Node here.
The experimental WebAssembly wide_arithmetic instructions are a big deal for crypto code when runtimes support them.
What I measured
The test program is libsodium’s benchmark suite, built from libsodium commit 8e3be8615ba6adcd7babaecf5e76f516890ba5fb.
I built one native baseline and several WebAssembly variants:
native x86-64, compiled with Zig using the local CPU target
plain WebAssembly
WebAssembly with lime1
WebAssembly with lime1 and simd128
WebAssembly with lime1, simd128, and wide_arithmetic
For the native reference, libsodium was built with -Dcpu=native. For wasm2c, the generated C was compiled with zig cc -O3 -march=native.
The native command was:
zig build -Denable_benchmarks -Doptimize=ReleaseFast -Dcpu=native -Diterations=3
The WebAssembly commands were the same shape, with a wasm32-wasi target and the feature-specific CPU strings:
zig build -Denable_benchmarks -Dtarget=wasm32-wasi -Doptimize=ReleaseFast -Diterations=3<br>zig build -Denable_benchmarks -Dtarget=wasm32-wasi -Doptimize=ReleaseFast -Dcpu=lime1 -Diterations=3<br>zig build -Denable_benchmarks -Dtarget=wasm32-wasi -Doptimize=ReleaseFast -Dcpu=lime1+simd128 -Diterations=3<br>zig build -Denable_benchmarks -Dtarget=wasm32-wasi -Doptimize=ReleaseFast -Dcpu=lime1+simd128+wide_arithmetic -Diterations=3
The host was an AMD Ryzen AI 9 HX 470 with 12 cores and 24 threads. CPU boost was disabled and the maximum CPU frequency was 2 GHz. The OS was Linux 7.1.0-rc7, and Zig was 0.17.0-dev.948+e949341b7.
The numbers below are the geometric mean of per-benchmark slowdowns relative to the native build. Lower is better. A value of 2.0 means “twice as slow as native” on this machine.
I used ITERATIONS=3, so the very small libsodium tests are noisy and quantized. Rows reporting zero time were excluded from the aggregate. I did not pin benchmark processes to specific cores. This is still useful for comparing broad runtime behavior, but don’t treat the last decimal place as meaningful.
Versions
For every runtime except WAVM, I used the latest stable release available on June 23, 2026, plus a stable release from roughly one year earlier and one from roughly two years earlier.
Runtime<br>2024<br>2025<br>2026
Bun<br>1.1.16<br>1.2.17<br>1.3.14
Node<br>22.3.0<br>24.2.0<br>26.3.1
WABT wasm2c<br>1.0.35<br>1.0.37<br>1.0.41
WasmEdge<br>0.14.0<br>0.14.1<br>0.17.0
Wasmer<br>4.3.2<br>6.0.1<br>7.1.0
Wasmtime<br>22.0.0<br>34.0.0<br>46.0.0
WAVM<br>n/a<br>n/a<br>nightly/2026-04-05
Wazero<br>1.7.3<br>1.9.0<br>1.12.0
WAVM is awkward to compare historically. The previous available release was a 2022 binary, and that binary refused to run on this machine. I only kept the 2026 nightly.<br>Very little code changes have been made since 2022. But it was previously consistently smoking the competition, even without code changes, it may still be competitive.
Baseline WebAssembly
This is the plain WebAssembly build, without lime1, SIMD, or wide arithmetic.
Lower is better:
Runtime<br>2024<br>2025<br>2026
WAVM<br>n/a<br>n/a<br>1.41
WasmEdge<br>1.66<br>1.98<br>partial
wasm2c<br>2.01<br>2.08<br>1.86
Wasmer<br>2.13<br>2.56<br>2.08
Wasmtime<br>2.67<br>2.54<br>2.41
Wazero<br>4.84<br>4.70<br>4.72
Node<br>8.60<br>8.22<br>7.95
Bun<br>27.41<br>26.42<br>8.77
There isn’t one universal trend.
Wasmtime steadily improved: 2.67x native in 2024, 2.54x in 2025, 2.41x in 2026. That’s not a revolution, but it is real progress.
Node also improved slowly, from 8.60x native to 7.95x native.
Wazero was basically flat: 4.84x, 4.70x, 4.72x. That’s not bad, but this benchmark doesn’t show a big speedup over the last two years.
Wasmer regressed in the 2025 release I tested, then recovered in 2026. The 2026 baseline is slightly faster than the 2024 baseline, but not by much.
wasm2c improved modestly in 2026. It remains one of the best options if ahead-of-time translation to native C is acceptable for your deployment model.
Bun is the outlier. Its 2024 and 2025...