iota-decide-4b-v0.3 (Macrocosmos, letter-readout 4B, self-hosted)v1.7 · 10 s rule
Data: JevBench v1.7.10, published 2026-10-26 · method v1.7 (10 s rule), measured under the rule
Capability 68.6 · rank #41 of 170 on the open-weights board
Last measured: 2026-10-26 · measurement release: v1.7.10
Apache-2.0 (HF metadata and README), public, not gated
intelligence
52.5
calibration
84.8
speed
87.5
cost
64.3
Composite (secondary)
69.2 · Composite rank #22
Cost and measurement conditions
$0.015 per 1,000 decisions (estimated)
ESTIMATE (*est.), base-model market reference through the frozen pricing_v15 module (installed 645fd82e): base Qwen/Qwen3.5-4B -> deepinfra:Qwen/Qwen3.5-4B at USD 0.03/0.15 per million input/output tokens. Estimated, not charged, not a quote from the author or any host. Tokens as reported by the server usage block: 1,008,925 input on 1,500 answered items, 0 output tokens (one forward pass per question, option-letter readout, no generation).
Measured p50 latency: 0.113 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 0.113 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 rented Verda GPU VM, 1x NVIDIA A100-SXM4-80GB (FIN-03, Finland, EU, pay-as-you-go non-spot, USD 2.215/h), instance id e352f0be-a001-4a77-83ff-8734642cf20f. Container with --network none (cut proven from inside before the sealed input), Hub offline, every credential unset, read-only weights, all 11 weight files sha256-verified; driven one request at a time. The standard self-hosted x2 + 0.15 s adjustment applies. Measured 26 Oct 2026 on the frozen v1.6-regular-20261012 self-hosted input (sha256 dfd36720...); determinism 50/50 bit-identical; VM and volume destroyed afterwards.
Measured latency over 1,500 decisions: p50 0.113 s · p95 0.163 s
0 decisions over 10 s.
A decision that takes longer than 10 seconds (measured time) counts as a wrong answer and as zero calibration for that item: each type's calibration is multiplied by the share of its decisions answered within 10 s. The limit uses the measured time (raw). The displayed adjusted time for self-hosted rows (2 × + 0.15 s) is an assumption and is not used for the limit.