decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) vs swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4)
As of Oct 15, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) 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.
swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4)
#33 Best current rank: #33 in Decision models, as of Oct 15, 2026.
| Category | decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) | swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) |
|---|---|---|
| Decision models | #4 · Near-SOTA · Decision models Margin 2.2727272727272663 JevBench · Oct 8, 2026 | #33 · #33 in Decision models Margin 14.393939393939391 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.
swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4): 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.
swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4): open weights.
Decision models: As of Oct 15, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) in Decision models at #4 against #33.
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) · swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4)
decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) or swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4)?
As of Oct 15, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) 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 swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) for Decision models?
As of Oct 15, 2026, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) leads swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) in Decision models at #4 against #33.