Nemotron Diffusion 8B (pst2154, optimized vLLM)v1.7 · 10 s rule

Data: JevBench v1.8.12, published 2026-11-16 · method v1.7 (10 s rule), re-scored from the recorded per-decision times

Capability 47.5 · rank #192 of 243 on the open-weights board

Last measured: 2026-10-04 · measurement release: v1.6.0

MIT (application code); modified vLLM runtime Apache-2.0; nvidia/Nemotron-Labs-Diffusion-8B keeps its upstream licence

Base model: nvidia/Nemotron-Labs-Diffusion-8Bsource

intelligence

20.4

calibration

74.5

speed

93.6

cost

55.5

Composite (secondary)

7.3 · Composite rank #207

Cost and measurement conditions

$0.030 per 1,000 decisions (estimated)

v1.5.4 published cost per 1,000 decisions carried (pricing rules unchanged; v1.6 item lengths differ): documented hosted-model estimate; no exact base-model floor applies

Measured p50 latency: 0.024 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: 0.20 s (est. incl. network (2x + 150 ms))

Self-hosted model: measured p50 0.024 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 = 0.20 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 (H100), offline read-only container

Measured latency over 1,500 decisions: p50 0.024 s · p95 0.036 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.

JevBench v1.6.43 values (method v1.6, before the 10 s rule)

Capability 47.46 · Composite 7.30 · rank #179 on the all-systems board · #140 open weights

intelligence 20.39 · calibration 74.54 · speed 93.83 · cost 55.49

v1.6 speed basis (124 items): p50 0.022 s · p95 0.032 s

These figures are kept for comparison. The current figures above are re-scored under the 10 s rule from the recorded per-decision times and replace them.

Published source