SPEC CPU result comparison

15th October 2026 - Normalized report

SPEC2026 INTrate: Standard -O2 generic - LLVM and GCC

Plain -O2

Please note that the same "optimization levels" mean different things to different compilers. For example, LLVM and LLVM-based compiler tend to be much more aggressive at -O2, often with the corresponding consequences to size of the generated binaries and compilation time. GCC is sometimes more aggressive at -O3. LLVM is also often by default less strict when it comes to standard compliance by default and performs optimizations GCC would only do with a special compilation option or at -Ofast. Keep this is mind when comparing different compilers.

AMD EPYC 8635P (zen5 based Sorano)

Run-times

Benchmark LLVM GCC
706.stockfish_r 100.00% 61.20%
707.ntest_r 100.00% 106.44%
708.sqlite_r 100.00% 97.14%
710.omnetpp_r 100.00% 89.16%
714.cpython_r 100.00% 95.83%
721.gcc_r 100.00% 97.59%
723.llvm_r 100.00% 99.16%
727.cppcheck_r 100.00% 98.94%
729.abc_r 100.00% 97.36%
734.vpr_r 100.00% 96.46%
735.gem5_r 100.00% 94.17%
750.sealcrypto_r 100.00% 88.84%
753.ns3_r 100.00% 100.00%
777.zstd_r 100.00% 94.95%
LLVM clang version 23.1.3 (/labs/mjambor/git/llvm 0d261d1ca552c95a8f007e061c787ac7132fbcbc), flang version 23.1.3 (/labs/mjambor/git/llvm 0d261d1ca552c95a8f007e061c787ac7132fbcbc)
GCC GCC 17.0.0 20261015 (experimental) (revision 84348add236100e5f69a3e9ec4f7b1038bf2b83d)
Naturally, the smaller the run-times, the better.

Non-debug executable sizes

Benchmark LLVM GCC
706.stockfish_r 100.00% 100.71%
707.ntest_r 100.00% 100.22%
708.sqlite_r 100.00% 86.41%
710.omnetpp_r 100.00% 98.12%
714.cpython_r 100.00% 94.23%
721.gcc_r 100.00% 96.54%
723.llvm_r 100.00% 115.25%
727.cppcheck_r 100.00% 108.55%
729.abc_r 100.00% 107.17%
734.vpr_r 100.00% 105.10%
735.gem5_r 100.00% 126.70%
750.sealcrypto_r 100.00% 123.53%
753.ns3_r 100.00% 104.99%
777.zstd_r 100.00% 100.59%
Smaller binary sizes are always better.