As of Oct 14, 2026, deck-31B (krishna765, frozen Gemma-4-31B-it, TorchAO FP8 dynamic) is ranked #16 in Decision models (since Oct 14, 2026; sources Decision Index Full and JevBench; methodology v1.0). Ranked #16 in Decision models.
The ruling, in plain English
Ranked #16 in Decision models.
Reliability
Index bins for deck-31B (krishna765, frozen Gemma-4-31B-it, TorchAO FP8 dynamic). Confidence on the horizontal axis, accuracy on the vertical axis.
Median 218.5 ms, same GPU.
$0.0475 per 1,000 decisions.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full deck31b (Gemma 4 31B) | 59.03 58.5–59.5 | 2026-10-14 | INDEP. | snap_decision-index_2026-10-14_release-v3|decision-index-0.3.2 |
| JevBench deck-31B (krishna765, frozen Gemma-4-31B-it, TorchAO FP8 dynamic) | 77.5907429125261 77.1–78.1 | 2026-10-08 | INDEP. | snap_jevbench_2026-10-08_v1.6.1|jevbench-v1.6.1 |
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Why |
|---|---|---|
| Decision models | #16 in this category | Ranked #16 in Decision models. |
Related pages
- Decision models
- Compare with the current leader in Decision models: vLLM-SR d3 (27B)
- Compare with the current leader in Decision models: linne-oak 1.0 (31B)
- Compare with the current leader in Decision models: Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
- Decision Index Full
- JevBench
Is deck-31B (krishna765, frozen Gemma-4-31B-it, TorchAO FP8 dynamic) SOTA?
Best current rank: #16 in Decision models, as of Oct 14, 2026.
What is deck-31B (krishna765, frozen Gemma-4-31B-it, TorchAO FP8 dynamic) best at?
As of Oct 14, 2026, deck-31B (krishna765, frozen Gemma-4-31B-it, TorchAO FP8 dynamic) is ranked #16 in Decision models (since Oct 14, 2026; sources Decision Index Full and JevBench).
How does deck-31B (krishna765, frozen Gemma-4-31B-it, TorchAO FP8 dynamic) rank in Decision models?
Best current rank: #16 in Decision models, as of Oct 14, 2026.