Li Benchmarks

qm_xtb_gfn greenvalidity pass

Tier 2 · wall_time · N=N=256 · variant algo_registry · OS linux

passpass — perf claims allowed when ratio is green

Source: latest.csv:perf_present

Wall-clock row exists only — no explicit correctness signal yet.

Ratio vs best competitor: 0.995 (99.5% of rust speed) (table SOTA: rust — best competitor; charts use rust = 1.0)
Best competitor value: 0.1062 s

No analytical verify rows in ingest yet. Run tier-1 with --verify so latest.csv exports verify_ulps / verify_within_1ulp.

Problem size: N=N=256 (family qm_xtb_gfn)
Category: physics
Pillar: physics
Package: lic
Li / catalog oracle (mean ± σ): 0.1067 ± 0.005109 s (n=20) / 0.1133 ± 0.01679 s (n=20) (cpp)
Ratio vs catalog oracle: 0.9417×
Best competitor: rust (0.1062 s)
Li relative speed vs SOTA: 0.995 (1.0 = rust speed)
Validity: validity pass
Threshold: 1.2×
Source: lic/benchmarks/workloads/tier2_physics/qm_xtb_gfn

PH ids: PH-5b

Compare oracle: cpp

Relative speed vs best competitor (rust) — SOTA = 1.0, higher is better. Absolute s values are in the table below.

Language comparison
Lang	Mean ± σ	Runs	Unit	Variant	OS
li	0.1067 ± 0.005109	20	s	release	linux
cpp	0.1133 ± 0.01679	20	s	release	linux
rust	0.1062 ± 0.006339	20	s	release	linux
julia	0.1064 ± 0.004795	20	s	release	linux
Metric: wall_time (value = mean of timed runs)