Lisp SBCL versus Java fastest programs Always look at the source code. These are only the fastest programs. Do some of them use manually vectorized SIMD? Look at the other programs. They may seem more-like a fair comparison to you. spectral-norm source secs mem gz busy cpu load Lisp SBCL 1.44 15,680 762 5.72 99% 99% 99% 99% Java 1.63 39,304 756 6.22 95% 97% 95% 95% fannkuch-redux source secs mem gz busy cpu load Lisp SBCL 9.63 32,388 1527 37.69 98% 95% 99% 99% Java 10.64 35,192 1282 41.91 99% 98% 99% 97% mandelbrot source secs mem gz busy cpu load Lisp SBCL 4.09 46,684 2447 16.19 99% 99% 99% 99% Java 4.15 69,136 796 16.29 98% 99% 98% 99% binary-trees source secs mem gz busy cpu load Lisp SBCL 2.84 529,972 932 7.09 73% 46% 63% 67% Java 2.48 1,722,848 835 7.88 98% 75% 71% 74% n-body source secs mem gz busy cpu load Lisp SBCL 7.83 17,892 1403 7.88 0% 0% 100% 0% Java 6.74 35,844 1489 6.82 1% 100% 1% 0% k-nucleotide source secs mem gz busy cpu load Lisp SBCL 10.29 512,240 2479 37.48 88% 99% 88% 90% Java 4.98 356,904 1812 16.25 78% 76% 96% 76% regex-redux source secs mem gz busy cpu load Lisp SBCL 15.34 925,000 1972 31.90 42% 49% 63% 53% Java 5.58 985,696 929 18.26 81% 77% 84% 85% pidigits source secs mem gz busy cpu load Lisp SBCL 3.34 607,800 493 3.38 0% 0% 100% 1% Java 0.93 36,552 764 0.98 2% 3% 1% 99% fasta source secs mem gz busy cpu load Lisp SBCL 4.71 18,072 1757 4.75 0% 0% 0% 100% Java 1.21 44,620 2543 3.58 89% 75% 65% 68% reverse-complement source secs mem gz busy cpu load Lisp SBCL 6.40 1,490,256 904 6.42 0% 0% 0% 100% Java 1.54 670,924 2183 3.51 46% 56% 48% 79% Lisp SBCL SBCL 2.1.1 Java openjdk 16 2021-03-16 OpenJDK Runtime Environment (build 16+36-2231) OpenJDK 64-Bit Server VM (build 16+36-2231, mixed mode, sharing) all Lisp SBCL programs & measurements all Java programs & measurements