Mirror
Data: JevBench v1.6.1, published 2026-10-06
Capability 25.8 · Not ranked in the current release
latency 2.4× Jev (v1.5 reference)
Last measured: 2026-10-02 · measurement release: v1.6.1
Apache-2.0 wrapper and Mirror release; upstream DeBERTa/model assets retain their own terms
intelligence
0.0
calibration
51.6
speed
73.5
cost
89.3
Composite (secondary)
0.0 · Composite rank #127
Cost and measurement conditions
$0.0023 per 1,000 decisions (estimated)
v1.5.4 published cost per 1,000 decisions carried (pricing rules unchanged; v1.6 item lengths differ): documented hosted-model estimate; no exact base-model floor applies
Measured p50 latency: 0.651 s (on-CPU, no network, loopback; not directly comparable with API latency, which we time end to end from our measuring host, network included)
Ranking and cap use: 1.45 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.651 s on-CPU, no network (timed on our CPU host over loopback). Not directly comparable with API latency, which we time end to end from our measuring host, network included. The ranking and latency cap use the same estimate for every self-hosted row: 2 × measured + 150 ms = 1.45 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
evaluator-owned CPU container, offline read-only, pinned cores