As of Oct 15, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) is tied for state of the art with low confidence in Decision models (since Oct 14, 2026; sources Decision Index Full and JevBench; methodology v1.0). Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) is co-SOTA in Decision models with low confidence because primary sources disagree beyond the margin of error (with vLLM-SR d3 (27B), linne-oak 1.0 (31B)).
The ruling, in plain English
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) is co-SOTA in Decision models with low confidence because primary sources disagree beyond the margin of error (with vLLM-SR d3 (27B), linne-oak 1.0 (31B)).
Reliability
Index bins for Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout). Confidence on the horizontal axis, accuracy on the vertical axis.
Median 104.1 ms, same GPU.
$0.2173 per 1,000 decisions.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full Perplexity Decider v1.1 (27B) | 62.75 62.3–63.3 | 2026-10-14 | INDEP. | snap_decision-index_2026-10-14_release-v3|decision-index-0.3.2 |
| JevBench Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) | 82.79186839726479 82.3–83.3 | 2026-10-08 | INDEP. | snap_jevbench_2026-10-08_v1.6.1|jevbench-v1.6.1 |
Where it sits in the succession
Related pages
Is Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) SOTA?
As of Oct 15, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) is tied for state of the art with low confidence in Decision models (since Oct 14, 2026; sources Decision Index Full and JevBench; methodology v1.0).
What is Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) best at?
As of Oct 15, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) is tied for state of the art with low confidence in Decision models (since Oct 14, 2026; sources Decision Index Full and JevBench).
How does Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) rank in Decision models?
Best current rank: #1 in Decision models, as of Oct 15, 2026.
When was Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) last SOTA?
As of Oct 15, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) last held Decision models from Oct 8, 2026 until Oct 14, 2026.