NInfer Qwen3.8-Flash-Next mixed
Data: JevBench v1.6.1, published 2026-10-06
Capability 69.7 · Not ranked in the current release
cost 2.5× Jev (v1.5 reference)
Last measured: 2026-10-02 · measurement release: v1.6.1
Qwen Community License 1.0 (model); Apache-2.0 (engine)
intelligence
49.0
calibration
90.4
speed
89.3
cost
42.5
Composite (secondary)
42.0 · Composite rank #31
Cost and measurement conditions
$0.082 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
Measured p50 latency: 0.080 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: 0.31 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.080 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 = 0.31 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 (RTXPRO6000), offline read-only container