Sign in
Decision models · Nov 6, 2026

Who is SOTA in Decision models?Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) & REAX 1.3 & GLiDE 27B

Typed answers with probabilities. The crown follows Decision Index Full and JevBench, both independent at weight 1. Vendor-reported numbers are display-only at weight 0. As of Nov 6, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) & REAX 1.3 &… Crown history, benchmark weights and methodology.

Standings · overall

The board

RSSHistory →
#ModelStateConfidenceWhy
1PEPerplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
Perplexity
Co-SOTA · Decision modelslowPerplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) is co-SOTA in Decision models with low confidence because primary…
1RREAX 1.3
REAX
Co-SOTA · Decision modelslowREAX 1.3 is co-SOTA in Decision models with low confidence because primary sources disagree beyond the margin of error (with GLiDE 27B,…
1FAGLiDE 27B
Fastino
Co-SOTA · Decision modelslowGLiDE 27B is co-SOTA in Decision models with low confidence because primary sources disagree beyond the margin of error (with REAX 1.3,…
2PEKnowLine 31B Gen1.5
PelaAI
Near-SOTA · Decision modelsmediumClose in Decision models: rank #2, 0.7 percentile points behind the leader.
3UNFlexDM-LoRA 2.1 · Gemma-4-31B
Unknown
Near-SOTA · Decision modelsmediumClose in Decision models: rank #3, 1.1 percentile points behind the leader.
4STSieve 31B v3
Sthānika AI
Near-SOTA · Decision modelsmediumClose in Decision models: rank #4, 1.5 percentile points behind the leader.
5TUTurion Jev 31B
Turion.AI
Near-SOTA · Decision modelsmediumClose in Decision models: rank #5, 1.8 percentile points behind the leader.
6VLvLLM-SR d3-ultra (Decision 3.0, 27B)
vLLM Semantic Router
Near-SOTA · Decision modelsmediumClose in Decision models: rank #6, 2.2 percentile points behind the leader.
7AMdecisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted)
Amin Roudaki
Near-SOTA · Decision modelsmediumClose in Decision models: rank #7, 2.3 percentile points behind the leader.
8BEBespoke Nimble v4.1 Max (27B)
Bespoke Labs
Near-SOTA · Decision modelsmediumClose in Decision models: rank #8, 2.6 percentile points behind the leader.
9H2H2O Lightning 31B v1.3.0
H2O.ai
Near-SOTA · Decision modelsmediumClose in Decision models: rank #9, 2.9 percentile points behind the leader.
10UNJeffan-31b-1710
Unknown
Near-SOTA · Decision modelsmediumClose in Decision models: rank #10, 3.3 percentile points behind the leader.
11UNliquamen (Gemma 4 31B)
Unknown
Near-SOTA · Decision modelsmediumClose in Decision models: rank #11, 3.6 percentile points behind the leader.
12UNWeMM-JEV-27B
Unknown
#12 in Decision modelsmediumRanked #12 in Decision models.
13BAbaselabs mammoth-1 (27B)
baselabs
Was SOTA · Decision modelsmediumWas SOTA in Decision models from 2026-10-20 to 2026-10-21. Currently ranked #13.
Embed

Badges for the leaders

Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)

CO-SOTA · Decision models · Nov 2026

[![CO-SOTA · Decision models · Nov 2026](https://isitsota.com/badge/pplx-decider-v1-1-27b/decision.svg)](https://isitsota.com/m/pplx-decider-v1-1-27b)

<a href="https://isitsota.com/m/pplx-decider-v1-1-27b"><img alt="CO-SOTA · Decision models · Nov 2026" src="https://isitsota.com/badge/pplx-decider-v1-1-27b/decision.svg" height="28"></a>

REAX 1.3

CO-SOTA · Decision models · Nov 2026

[![CO-SOTA · Decision models · Nov 2026](https://isitsota.com/badge/reax-1-3/decision.svg)](https://isitsota.com/m/reax-1-3)

<a href="https://isitsota.com/m/reax-1-3"><img alt="CO-SOTA · Decision models · Nov 2026" src="https://isitsota.com/badge/reax-1-3/decision.svg" height="28"></a>

GLiDE 27B

CO-SOTA · Decision models · Nov 2026

[![CO-SOTA · Decision models · Nov 2026](https://isitsota.com/badge/glide-v1-2-1-loop/decision.svg)](https://isitsota.com/m/glide-v1-2-1-loop)

<a href="https://isitsota.com/m/glide-v1-2-1-loop"><img alt="CO-SOTA · Decision models · Nov 2026" src="https://isitsota.com/badge/glide-v1-2-1-loop/decision.svg" height="28"></a>

Calibration

Reliability · Turion Jev 31B

Confidence on the horizontal axis, accuracy on the vertical axis. Larger marks carry more weight.

Display only

Self-reported claims

No vendor-reported row is in this snapshot. Vendor-reported numbers are display-only at weight 0.

Related

Best page and recent changes

Best AI model for decision models

What is a decision model

Evidence recipe

What can move this crown

Who is SOTA in Decision models?

As of Nov 6, 2026, Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) & REAX 1.3 & GLiDE 27B are tied for state of the art with low confidence in Decision models (since Nov 6, 2026; sources JevBench and Decision Index Full; methodology v1.0).

Since when is the Decision models crown current?

The current crown in Decision models has held since Nov 6, 2026.

What is a decision model?

A decision model takes state, as text or as images, plus a typed question. It returns a typed answer with probabilities rather than free text. Output types: noul (yes/no/unknown), choice, score, multi-label.

How is calibration ranked?

The calibration slice ranks the lowest ECE among models in the top quartile of accuracy, so a constant probability cannot take the slice. Brier breaks ECE ties.

Do vendor-reported decision numbers count?

Vendor-reported numbers are display-only at weight 0.