An independent benchmark of TypeSafe's Jev against open, CPU-only stacks.
10,000 decisions · 4 datasets · Apple M5 Pro · CPU · batch = 1.
One exception, disclosed: Laya's row is Apple MPS, because
laya.load() auto-selects it. Its like-for-like CPU latency is
59.5 / 78.0 / 61.9 / 309.0 ms — about 3× higher.
Mean p50 latency across the four tasks (log scale). Jev's latency is dominated by network round-trip — see the repo's limitations.
Same option text for every stack. Neither condition is neutral: the rewrite moves Jev +0.5 pp, the bi-encoder +6.3 pp, and the cross-encoder −4.3 pp.
Cross-encoder cost grows linearly with option count; Jev's is flat (381 ms at 2 options, 392 ms at 77). Extrapolated from measured points.