Winnow-12B Q8
Data: JevBench v1.6.1, published 2026-10-06
Capability 71.2 · rank #13 of 92 on the open-weights board
Last measured: 2026-10-02 · measurement release: v1.6.1
Apache-2.0, including the applicable Gemma 4 base/derivative licence terms
intelligence
59.5
calibration
83.0
speed
86.7
cost
56.6
Composite (secondary)
68.9 · Composite rank #7
Cost and measurement conditions
$0.028 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: 0.117 s (on-GPU, 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: 0.38 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.117 s on-GPU, no network (timed on our GPU 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 = 0.38 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
evaluator-owned Lium GPU pod (RTX6000), offline read-only container