iota-decide-4b-v0.4 (Macrocosmos, letter-readout 4B, self-hosted)v1.7 · 10 s rule
Data: JevBench v1.8.1, published 2026-10-30 · method v1.7 (10 s rule), measured under the rule
Capability 74.0 · Not ranked in the current release
Measured on the 27 Oct 2026 draw, which is not yet equated to the reference scale; stronger anchor runs for that draw are being measured. Shown unranked until then.
Last measured: 2026-10-29 · measurement release: v1.8.1
Apache-2.0 (HF metadata and README), public, not gated
intelligence
60.2
calibration
87.8
speed
92.2
cost
83.0
Composite (secondary)
78.6 · Not ranked on this board
Cost and measurement conditions
$0.0037 per 1,000 decisions (estimated)
GPU-time estimate from v1.8.0: one monthly-rented RTX PRO 6000 96 GB, EUR 999/month / 730 hours, ECB USD 1.1133/EUR dated 28 Oct 2026, USD 1.5235/hour; average load 70%. Architecture: small qwen, 4B active parameters; throughput 61525 tokens/s (architecture-class calibration, 29 Oct 2026, efficient-engine prefill; capped at 100,000 tokens/s). The row's own scored cost basis: 558,044 input + 0 output tokens over 1,489 decisions. Generated tokens are counted at the same throughput as prefill. GPU-time cost USD 0.00368268048708357/1,000; old list-price estimate USD 0.0112433310946944/1,000 (deepinfra:Qwen/Qwen3.5-4B at USD 0.03/M input and USD 0/M output). Applied min(old list-price estimate, GPU-time cost) = USD 0.00368268048708357/1,000. Estimated, not a bill. USD 0.00368268049 per 1,000 decisions on the frozen 1,489-item common set of this draw (USD 0.00420412617 over all 1,500 items).
p50 latency: 0.2 s
Self-hosted latency estimate under the shared method (assumption, not measured)
Evaluator-owned rented Verda GPU VM, 1x NVIDIA RTX PRO 6000 Blackwell Server Edition (FIN-03, Finland, EU, pay-as-you-go non-spot, USD 2.674/h). 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. Measured 29 Oct 2026 on the frozen v1.6-regular-20261027 self-hosted input (sha256 9b2f32ed...); determinism 50/50 bit-identical; VM and volume destroyed afterwards.
Measured latency over 1,500 decisions: p50 0.033 s · p95 0.063 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.