Jobe Qwen3.5-4B (frozen)
Data: JevBench v1.6.1, published 2026-10-06
Capability 55.1 · Not ranked in the current release
Last measured: 2026-09-27T18:49:51+00:00 · measurement release: v1.4.2.2
MIT code; Apache-2.0 weights
intelligence
44.1
calibration
66.1
speed
85.6
cost
59.5
Composite (secondary)
46.9 · Not ranked on this board
Cost and measurement conditions
$0.022 per 1,000 decisions (estimated)
ESTIMATE: hosted-provider price, DeepInfra Qwen3.5-4B hosted reference list price $0.03/M in, $0.0/M out (same underlying weights; one forward pass, no generated tokens) x 396 input and 0 output tokens per decision (input tokens measured (the system's own count))
Measured p50 latency: 0.135 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: 0.42 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.135 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 = 0.42 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
our GPU (lium.io RTX A6000 48 GB), in-process, serial