decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) vs RSI-Jev v6.1 VL 27B (effort auto)
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 RSI-Jev v6.1 VL 27B (effort auto) 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.
RSI-Jev v6.1 VL 27B (effort auto)
Yes. Yes on Decision models › Vision (calibration). Not the overall leader.
| Category | decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) | RSI-Jev v6.1 VL 27B (effort auto) |
|---|---|---|
| Decision models | #4 · Near-SOTA · Decision models Margin 2.2727272727272663 JevBench · Oct 8, 2026 | #25 · #25 in Decision models Margin 11.515151515151516 Jev Decision Index · Oct 14, 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.
RSI-Jev v6.1 VL 27B (effort auto): 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.
RSI-Jev v6.1 VL 27B (effort auto): 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 RSI-Jev v6.1 VL 27B (effort auto) in Decision models at #4 against #25.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) · RSI-Jev v6.1 VL 27B (effort auto)
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) or RSI-Jev v6.1 VL 27B (effort auto)?
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 RSI-Jev v6.1 VL 27B (effort auto) 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 RSI-Jev v6.1 VL 27B (effort auto) 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 RSI-Jev v6.1 VL 27B (effort auto) in Decision models at #4 against #25.