SPEC CPU result comparison

15th October 2026 - Normalized report

SPEC2026 INTrate: Standard native -Ofast - Released GCCs vs Trunk

-Ofast -march=native -mtune=native

AMD EPYC 8635P (zen5 based Sorano)

Run-times

Benchmark GCC 16 Trunk
706.stockfish_r 100.00% 98.13%
707.ntest_r 100.00% 100.00%
708.sqlite_r 100.00% 100.00%
710.omnetpp_r 100.00% 100.93%
714.cpython_r 100.00% 98.92%
721.gcc_r 100.00% 100.84%
723.llvm_r 100.00% 100.64%
727.cppcheck_r 100.00% 96.79%
729.abc_r 100.00% 100.00%
734.vpr_r 100.00% 97.14%
735.gem5_r 100.00% 100.00%
750.sealcrypto_r 100.00% 46.57%
753.ns3_r 100.00% 100.00%
777.zstd_r 100.00% 99.28%
GCC 15 GCC 15.3.0 (revision 4db0e8df15bef836558857c291c323add11d035c)
GCC 16 GCC 16.2.0 (revision 78d4ac73dd391005b895a6148cd9831e28e1208b)
Trunk GCC 17.0.0 20261015 (experimental) (revision 84348add236100e5f69a3e9ec4f7b1038bf2b83d)
Naturally, the smaller the run-times, the better.
See also continuous gcc branch benchmarking at https://lnt.opensuse.org/db_default/v4/SPEC/spec_report/branch.

Non-debug executable sizes

Benchmark GCC 16 Trunk
706.stockfish_r 100.00% 100.47%
707.ntest_r 100.00% 99.80%
708.sqlite_r 100.00% 100.21%
710.omnetpp_r 100.00% 98.84%
714.cpython_r 100.00% 99.55%
721.gcc_r 100.00% 99.53%
723.llvm_r 100.00% 99.64%
727.cppcheck_r 100.00% 98.91%
729.abc_r 100.00% 98.98%
734.vpr_r 100.00% 98.63%
735.gem5_r 100.00% 99.43%
750.sealcrypto_r 100.00% 98.87%
753.ns3_r 100.00% 99.05%
777.zstd_r 100.00% 100.05%
Smaller binary sizes are always better.