ML-KEM·Key encapsulation·NIST level 5

ML-KEM-1024

ML-KEM (FIPS 203) is a lattice-based key encapsulation mechanism, standardized by NIST in August 2024. It replaces RSA and elliptic-curve Diffie-Hellman for establishing shared secrets in a post-quantum world.

Latest run2026-10-28 11:58 UTC
commitfb7d298
CPU
Xeon Platinum 8488C
Measured on
c7i.large
OS / Kernel
24.04.4 LTS
liboqs
0.15.0
Wall clock
32m 35s
CPU steal
<0.01%

Parameters

Family
ML-KEM
Parameter set
1024
Public key
1.53 KB
Private key
3.09 KB
Ciphertext
1.53 KB
Iterations / op
1,000
liboqs key
ML-KEM-1024

Regulatory approval status

Whether this algorithm family is approved/recommended for use under three regimes. Every badge links to its source — click through before citing this elsewhere.

keygenGenerate a fresh key pair.
168 of 168 runs
Mean
14.0 µs
95% CI on mean
±1.26%
Median
13.5 µs
p95
16.8 µs
p99
23.7 µs
Stdev
2.9 µs
Min
12.8 µs
Ops/sec
71,242

Mean is known to 13.86–14.21 µs across 1,000 iterations. A 95% confidence interval on the mean, not a prediction interval for a single operation. It says how precisely the average is known from this run's samples; the standard deviation says how much the individual samples scattered.

Mean over time

Click any point to view the GitHub Actions run that produced it.

encapEncapsulate: produce a shared secret and ciphertext under the recipient's public key.
168 of 168 runs
Mean
15.1 µs
95% CI on mean
±1.48%
Median
14.6 µs
p95
16.4 µs
p99
24.3 µs
Stdev
3.6 µs
Min
14.0 µs
Ops/sec
66,408

Mean is known to 14.84–15.28 µs across 1,000 iterations. A 95% confidence interval on the mean, not a prediction interval for a single operation. It says how precisely the average is known from this run's samples; the standard deviation says how much the individual samples scattered.

Mean over time

Click any point to view the GitHub Actions run that produced it.

decapDecapsulate: recover the shared secret from the ciphertext using the private key.
168 of 168 runs
Mean
16.8 µs
95% CI on mean
±0.63%
Median
16.3 µs
p95
18.5 µs
p99
26.1 µs
Stdev
1.7 µs
Min
15.7 µs
Ops/sec
59,590

Mean is known to 16.67–16.89 µs across 1,000 iterations. A 95% confidence interval on the mean, not a prediction interval for a single operation. It says how precisely the average is known from this run's samples; the standard deviation says how much the individual samples scattered.

Mean over time

Click any point to view the GitHub Actions run that produced it.

Know the cost of post-quantum migration.

Coldproof