decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) vs Sieve 31B
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 Sieve 31B in 0 of 1 shared categories.
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.
Sieve 31B
Close. Near-SOTA in Decision models, rank #3.
| Category | decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) | Sieve 31B |
|---|---|---|
| Decision models | #4 · Near-SOTA · Decision models Margin 2.2727272727272663 JevBench · Oct 8, 2026 | #3 · Near-SOTA · Decision models Margin 1.818181818181813 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.
Sieve 31B: 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.
Sieve 31B: open weights.
Decision models: As of Oct 14, 2026, Sieve 31B leads decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) in Decision models at #3 against #4.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) · Sieve 31B
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) or Sieve 31B?
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 Sieve 31B in 0 of 1 shared categories.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) or Sieve 31B for Decision models?
As of Oct 14, 2026, Sieve 31B leads decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) in Decision models at #3 against #4.