Imajev-4B (RTX 5090)
Data: JevBench v1.6.1, published 2026-10-06
Capability 61.9 · rank #31 of 92 on the open-weights board
Last measured: 2026-10-02 · measurement release: v1.6.1
not recorded
intelligence
34.6
calibration
89.2
speed
90.5
cost
63.3
Composite (secondary)
28.7 · Composite rank #47
Cost and measurement conditions
$0.017 per 1,000 decisions (estimated)
v1.5.4 published cost per 1,000 decisions carried (pricing rules unchanged; v1.6 item lengths differ): ESTIMATE (I-2): measured input tokens; zero generated output tokens for signed logits readout. M2 floor uses the 25 Sep 2026 DeepInfra Qwen3.5-4B snapshot rates (USD 0.03/M input, USD 0.15/M output); the snapshot records deprecation on 11 Jun 2026 and replacement by Qwen3.5-9B.
Measured p50 latency: 0.071 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: 0.29 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.071 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 = 0.29 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 (RTX 5090), offline read-only container