metask-jev-rain-12B
Data: JevBench v1.6.39, published 2026-10-22
Capability 78.3 · Not ranked in the current release
registry ranked=false or no composite
Last measured: 2026-10-09 · measurement release: v1.6.2
Licence not stated
intelligence
66.7
calibration
89.8
speed
76.0
cost
52.7
Composite (secondary)
68.7 · Not ranked on this board
Cost and measurement conditions
$0.038 per 1,000 decisions (estimated)
ESTIMATE: OpenRouter google/gemma-3-12b-it public listed sibling of same Gemma family/12B size class; exact google/gemma-4-12b-it absent (endpoint404 and models-list checked2026-10-09). USD0.05/M input and0.15/M output, applied to native measured engine-basis usage; not a Gemma4 publictariff or rentalcost. Follows trusted PREP-OPEN-WEIGHTS-PROMPT Gemma4-12B fallback and v16 cygnet/decider12b precedent.
Measured p50 latency: 0.092 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: 0.33 s (est. incl. network (2x + 150 ms))
Self-hosted model: measured p50 0.092 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 = 0.33 s. Model authors can ask us to time a hosted endpoint instead (on request).
x2 + 0.15 s (assumption, not measured)
Setup not stated