decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) vs OneJev1.5-27B
As of Oct 14, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads OneJev1.5-27B in 1 of 1 shared categories: Decision models.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted)
Yes. Yes on Decision models (price per 1,000 decisions). Not the overall leader.
OneJev1.5-27B
#18 Best current rank: #18 in Decision models, as of Oct 14, 2026.
| Category | decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) | OneJev1.5-27B |
|---|---|---|
| Decision models | #4 · Near-SOTA · Decision models Margin 2.2727272727272663 JevBench · Oct 8, 2026 | #18 · #18 in Decision models Margin 7.878787878787875 Jev Decision Index · Oct 14, 2026 |
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted): price per 1M tokens is unset in the catalog.
OneJev1.5-27B: price per 1M tokens is unset in the catalog.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted): open weights.
OneJev1.5-27B: open weights.
Decision models: As of Oct 14, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads OneJev1.5-27B in Decision models at #4 against #18.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) · OneJev1.5-27B
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) or OneJev1.5-27B?
As of Oct 14, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads OneJev1.5-27B in 1 of 1 shared categories: Decision models.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) or OneJev1.5-27B for Decision models?
As of Oct 14, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads OneJev1.5-27B in Decision models at #4 against #18.