I run pyperformance.It seems django_template is significant faster.# Without PGO+LTO./python -m perf compare_to -G --min-speed=2 default.json patched.jsonSlower (6):- scimark_monte_carlo: 217 ms +- 9 ms -> 237 ms +- 10 ms: 1.09x slower (+9%)- scimark_lu: 326 ms +- 14 ms -> 351 ms +- 20 ms: 1.08x slower (+8%)- float: 219 ms +- 4 ms -> 226 ms +- 8 ms: 1.03x slower (+3%)- crypto_pyaes: 208 ms +- 2 ms -> 213 ms +- 2 ms: 1.02x slower (+2%)- pickle: 20.1 us +- 0.2 us -> 20.6 us +- 0.4 us: 1.02x slower (+2%)- xml_etree_iterparse: 184 ms +- 3 ms -> 188 ms +- 3 ms: 1.02x slower (+2%)Faster (10):- django_template: 315 ms +- 4 ms -> 287 ms +- 3 ms: 1.10x faster (-9%)- logging_format: 25.9 us +- 0.3 us -> 24.7 us +- 0.3 us: 1.05x faster (-5%)- logging_simple: 21.6 us +- 0.2 us -> 20.6 us +- 0.4 us: 1.05x faster (-5%)- sympy_str: 399 ms +- 3 ms -> 381 ms +- 2 ms: 1.05x faster (-5%)- unpack_sequence: 117 ns +- 6 ns -> 112 ns +- 0 ns: 1.04x faster (-4%)- sympy_expand: 886 ms +- 7 ms -> 851 ms +- 7 ms: 1.04x faster (-4%)- regex_effbot: 5.00 ms +- 0.09 ms -> 4.84 ms +- 0.11 ms: 1.03x faster (-3%)- xml_etree_process: 185 ms +- 3 ms -> 180 ms +- 4 ms: 1.02x faster (-2%)- nqueens: 215 ms +- 3 ms -> 211 ms +- 3 ms: 1.02x faster (-2%)- telco: 16.0 ms +- 0.6 ms -> 15.6 ms +- 0.4 ms: 1.02x faster (-2%)Benchmark hidden because not significant (44)# With PGO+LTO$ ./python -m perf compare_to -G --min-speed=2 default-opt.json patched-opt.jsonSlower (8):- xml_etree_process: 179 ms +- 3 ms -> 195 ms +- 3 ms: 1.09x slower (+9%)- xml_etree_generate: 208 ms +- 5 ms -> 224 ms +- 3 ms: 1.08x slower (+8%)- xml_etree_iterparse: 190 ms +- 5 ms -> 203 ms +- 3 ms: 1.07x slower (+7%)- pickle_list: 6.80 us +- 0.30 us -> 7.18 us +- 0.72 us: 1.06x slower (+6%)- genshi_text: 72.8 ms +- 1.1 ms -> 76.3 ms +- 0.8 ms: 1.05x slower (+5%)- mako: 32.6 ms +- 0.1 ms -> 34.1 ms +- 0.6 ms: 1.05x slower (+5%)- unpickle_pure_python: 713 us +- 12 us -> 744 us +- 16 us: 1.04x slower (+4%)- scimark_sor: 375 ms +- 13 ms -> 383 ms +- 11 ms: 1.02x slower (+2%)Faster (14):- django_template: 327 ms +- 3 ms -> 296 ms +- 2 ms: 1.10x faster (-9%)- scimark_lu: 339 ms +- 20 ms -> 309 ms +- 13 ms: 1.10x faster (-9%)- sympy_str: 418 ms +- 4 ms -> 387 ms +- 3 ms: 1.08x faster (-7%)- sympy_expand: 926 ms +- 5 ms -> 860 ms +- 5 ms: 1.08x faster (-7%)- logging_simple: 22.4 us +- 0.3 us -> 21.0 us +- 0.3 us: 1.07x faster (-6%)- scimark_fft: 741 ms +- 61 ms -> 697 ms +- 25 ms: 1.06x faster (-6%)- telco: 17.6 ms +- 0.4 ms -> 16.6 ms +- 0.4 ms: 1.06x faster (-5%)- logging_format: 26.5 us +- 0.3 us -> 25.3 us +- 0.3 us: 1.05x faster (-5%)- sqlite_synth: 7.35 us +- 0.16 us -> 7.08 us +- 0.18 us: 1.04x faster (-4%)- scimark_sparse_mat_mult: 8.83 ms +- 0.42 ms -> 8.51 ms +- 0.37 ms: 1.04x faster (-4%)- pathlib: 43.1 ms +- 0.6 ms -> 41.7 ms +- 0.7 ms: 1.03x faster (-3%)- html5lib: 193 ms +- 7 ms -> 188 ms +- 7 ms: 1.03x faster (-3%)- richards: 149 ms +- 3 ms -> 145 ms +- 2 ms: 1.02x faster (-2%)- pickle_pure_python: 1.01 ms +- 0.01 ms -> 984 us +- 20 us: 1.02x faster (-2%)Benchmark hidden because not significant (38)