# torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) vs vLLM-SR d3 (27B)

As of Oct 15, 2026, torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) leads vLLM-SR d3 (27B) in 0 of 1 shared categories.

torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout): price per 1M tokens is unset in the catalog.

vLLM-SR d3 (27B): price per 1M tokens is unset in the catalog.

torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout): open weights.

vLLM-SR d3 (27B): open weights.

- Which to pick, Decision models: As of Oct 15, 2026, vLLM-SR d3 (27B) leads torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) in Decision models at #1 against #35.

As of Oct 15, 2026, torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) is ranked #35 in Decision models (since Oct 15, 2026; sources JevBench; methodology v1.0).

As of Oct 15, 2026, vLLM-SR d3 (27B) is tied for state of the art with low confidence in Decision models (since Oct 14, 2026; sources Decision Index Full; methodology v1.0).