# 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): 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.

- Which to pick, 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.

As of Oct 14, 2026, Cygnet (blockbrain, frozen Gemma-4-12B-it) is ranked #45 in Decision models (since Oct 14, 2026; sources JevBench; methodology v1.0).

As of Oct 14, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) is state of the art in Decision models (since Oct 8, 2026; sources JevBench price; methodology v1.0).