decisor-4b
Data: JevBench v1.6.39, published 2026-10-22
Capability 45.7 · rank #98 of 139 on the open-weights board
Last measured: 2026-10-09 · measurement release: v1.6.3
Licence not stated
intelligence
39.6
calibration
51.9
speed
91.9
cost
64.0
Composite (secondary)
35.3 · Composite rank #61
Cost and measurement conditions
$0.016 per 1,000 decisions (estimated)
ESTIMATE (base-model reference; self-hosted open weights with no per-token tariff of their own). Exact base model Qwen/Qwen3.5-4B (author model card base_model, revision 1e7f195c) resolved under the v1.5-M2 base-model reference rule to deepinfra:Qwen/Qwen3.5-4B at USD 0.03 per 1M input and USD 0.15 per 1M output in the frozen 25 Sep 2026 price cut-off snapshot (METHOD-v1.5-ADDENDUM-PRICING-INTERPRETATION-1 I-2/I-3); the listing was deprecated after the cut-off and stays the frozen reference. Output tokens priced at the reference output price. Replaces the larger-base proxy used at publication (Qwen3.5-9B Darkbloom endpoint, USD 0.08/0.13 per 1M). This row's usage on the common cost basis (1,479 items): 771,182 input and 1,479 output tokens. Estimated, not charged.
Measured p50 latency: 0.048 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: 0.25 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.048 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 = 0.25 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
Setup not stated