Quyet-1.0-Tiny (Chinh Nguyen, mmBERT-small encoder (16 layers kept) with fixed heads)
Data: JevBench v1.6.1, published 2026-10-06
Capability 31.1 · rank #83 of 92 on the open-weights board
Last measured: 2026-10-04 · measurement release: v1.6.1
apache-2.0
intelligence
3.7
calibration
58.5
speed
95.1
cost
88.4
Composite (secondary)
0.1 · Composite rank #116
Cost and measurement conditions
$0.0024 per 1,000 decisions (estimated)
v1.5.8 fast-lane delivery row (combined v1.5.8 preview, not yet published) cost per 1,000 decisions carried (pricing rules unchanged; v1.6 item lengths differ): ESTIMATE (v1.5-M2 base-model reference; self-hosted open weights, no public tariff): DeepInfra base-size encoders (bge-base, e5-base, gte-base, all-mpnet-base) $0.005/M input (mmBERT-small 16-layer, 183M; base-size class reference, errs high vs the small-encoder $0.004 class) x the package's own measured usage.input_tokens; one forward pass, nothing generated; run in process on 1x H100 80GB (Lium), quyet 1.0.0; estimated, not charged
Measured p50 latency: 0.013 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: 0.18 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.013 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 = 0.18 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, 1x NVIDIA H100 80GB, weights fetched in a separate model-only container, scored run inside docker --network none (loopback only, no secrets, label-free inputs); pod destroyed afterwards; paid public fast-lane evaluation, 4 Oct 2026 (order 3643732b)