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). decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads Decision models on price per 1,000 decisions since 2026-10-08. The field is models within 5 points of the accuracy leader.
The ruling, in plain English
Close in Decision models: rank #4, 2.3 percentile points behind the leader.
$0.0408 per 1,000 decisions.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| JevBench decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) | 79.56974174390604 79.1–80.1 | 2026-10-08 | INDEP. | snap_jevbench_2026-10-08_v1.6.1|jevbench-v1.6.1 |
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Why |
|---|---|---|
| Decision models | Near-SOTA | Close in Decision models: rank #4, 2.3 percentile points behind the leader. |
Related pages
Is decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) SOTA?
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).
What is decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) best at?
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 near state of the art, rank #4 in Decision models (since Oct 14, 2026; sources JevBench).
How does decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) rank in Decision models?
Best current rank: #4 in Decision models, as of Oct 14, 2026.