# Is torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) SOTA?

As of Oct 14, 2026, torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) is ranked #35 in Decision models (since Oct 14, 2026; sources JevBench; methodology v1.0).

Best current rank: #35 in Decision models, as of Oct 14, 2026.

As of Oct 14, 2026, torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) is ranked #35 in Decision models (since Oct 14, 2026; sources JevBench; methodology v1.0). Ranked #35 in Decision models.

Methodology v1.0. Computed automatically.

- Decision models: RANKED #35 — Ranked #35 in Decision models.