decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) vs Eikos-27B (caiovicentino1, Qwen3.8-27B)
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 Eikos-27B (caiovicentino1, Qwen3.8-27B) 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)
Yes. Yes on Decision models (price per 1,000 decisions). Not the overall leader.
Eikos-27B (caiovicentino1, Qwen3.8-27B)
#9 Best current rank: #9 in Decision models, as of Oct 14, 2026.
| Category | decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) | Eikos-27B (caiovicentino1, Qwen3.8-27B) |
|---|---|---|
| Decision models | #4 · Near-SOTA · Decision models Margin 2.2727272727272663 JevBench · Oct 8, 2026 | #9 · #9 in Decision models Margin 4.545454545454547 JevBench · Oct 8, 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.
Eikos-27B (caiovicentino1, Qwen3.8-27B): 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.
Eikos-27B (caiovicentino1, Qwen3.8-27B): closed 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 Eikos-27B (caiovicentino1, Qwen3.8-27B) in Decision models at #4 against #9.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) · Eikos-27B (caiovicentino1, Qwen3.8-27B)
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) or Eikos-27B (caiovicentino1, Qwen3.8-27B)?
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 Eikos-27B (caiovicentino1, Qwen3.8-27B) 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 Eikos-27B (caiovicentino1, Qwen3.8-27B) 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 Eikos-27B (caiovicentino1, Qwen3.8-27B) in Decision models at #4 against #9.