Compare · 2026-10-14

decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) vs Fastino GLiDE no-thinking (28B)

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 Fastino GLiDE no-thinking (28B) in 1 of 1 shared categories: Decision models.

Categorydecisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted)Fastino GLiDE no-thinking (28B)
Decision models
#4 · Near-SOTA · Decision models
Margin 2.2727272727272663
JevBench · Oct 8, 2026
#12 · #12 in Decision models
Margin 5.454545454545453
Jev Decision Index · Oct 14, 2026
Price per 1M tokens

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.

Fastino GLiDE no-thinking (28B): price per 1M tokens is unset in the catalog.

Open weights

decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted): open weights.

Fastino GLiDE no-thinking (28B): closed 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 Fastino GLiDE no-thinking (28B) in Decision models at #4 against #12.

decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) · Fastino GLiDE no-thinking (28B)

decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) or Fastino GLiDE no-thinking (28B)?

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 Fastino GLiDE no-thinking (28B) 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 Fastino GLiDE no-thinking (28B) 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 Fastino GLiDE no-thinking (28B) in Decision models at #4 against #12.