Cygnet (blockbrain, frozen Gemma-4-12B-it) vs decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted)
As of Oct 14, 2026, Cygnet (blockbrain, frozen Gemma-4-12B-it) leads decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) in 0 of 1 shared categories.
Cygnet (blockbrain, frozen Gemma-4-12B-it)
#45 Best current rank: #45 in 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)
Yes. Yes on Decision models (price per 1,000 decisions). Not the overall leader.
| Category | Cygnet (blockbrain, frozen Gemma-4-12B-it) | decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) |
|---|---|---|
| Decision models | #45 · #45 in Decision models Margin 19.696969696969703 JevBench · Oct 8, 2026 | #4 · Near-SOTA · Decision models Margin 2.2727272727272663 JevBench · Oct 8, 2026 |
Cygnet (blockbrain, frozen Gemma-4-12B-it): 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): price per 1M tokens is unset in the catalog.
Cygnet (blockbrain, frozen Gemma-4-12B-it): open weights.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted): 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 Cygnet (blockbrain, frozen Gemma-4-12B-it) in Decision models at #4 against #45.
Cygnet (blockbrain, frozen Gemma-4-12B-it) · decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted)
Cygnet (blockbrain, frozen Gemma-4-12B-it) or decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted)?
As of Oct 14, 2026, Cygnet (blockbrain, frozen Gemma-4-12B-it) leads decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) in 0 of 1 shared categories.
Cygnet (blockbrain, frozen Gemma-4-12B-it) or decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) 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 Cygnet (blockbrain, frozen Gemma-4-12B-it) in Decision models at #4 against #45.