verdict-small (Manavarya09, multilingual-e5-small 118M)
Data: JevBench v1.6.1, published 2026-10-06
Capability 37.6 · rank #76 of 92 on the open-weights board
Last measured: 2026-10-02 · measurement release: v1.6.1
Apache-2.0 (verdictml code and the Manav2op/verdict-small checkpoint over intfloat/multilingual-e5-small)
intelligence
2.3
calibration
72.9
speed
89.5
cost
100.0
Composite (secondary)
0.0 · Composite rank #118
Cost and measurement conditions
$0.0009 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: 0.049 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: 0.25 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.049 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 = 0.25 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