Decision models SOTA: Bobcat 1.3 (31B)

CategoryDecision models· Decision models

Also in Decision models:VisionC

Decision models · Oct 14, 2026

Who is SOTA in Decision models?

Bobcat 1.3 (31B)

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 Oct 14, 2026, Bobcat 1.3 (31B) is state of the art in Decision models (since Oct 14, 2026; sources Decision Index latency; methodology v1.0).

Overall Open weights Calibration Latency Price Hosted ≤ 32B Best per $

Lowest same-GPU median milliseconds among models within 5 points of the accuracy leader. Hosted API round-trip stays off this slice.

Standings · latency

The board

RSS History →

#	Model	State	Confidence	Why
1	UNBobcat 1.3 (31B) Unknown	SOTA · Decision models	medium	Bobcat 1.3 (31B) leads Decision models on same-GPU latency since 2026-10-14. The field is models within 5 points of the accuracy leader.
2	UNDecider 31B (NVFP4) Unknown	Near-SOTA · Decision models	medium	Ranked #2 in Decision models on same-GPU latency. Decider 31B (NVFP4) is inside the field.
3	VLvLLM-SR d3 (27B) vLLM Semantic Router	Near-SOTA · Decision models	medium	Ranked #3 in Decision models on same-GPU latency. vLLM-SR d3 (27B) is inside the field.
4	FIDarwin-27B-ZTC FINAL_Bench	#4 in Decision models	medium	Ranked #4 in Decision models on same-GPU latency. Darwin-27B-ZTC is inside the field.
5	PEPerplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) Perplexity	#5 in Decision models	medium	Ranked #5 in Decision models on same-GPU latency. Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) is inside the field.
6	MIlinne-oak 1.0 (31B) MISA-AICORE	#6 in Decision models	medium	Ranked #6 in Decision models on same-GPU latency. linne-oak 1.0 (31B) is inside the field.
7	STSieve 31B Sthānika AI	#7 in Decision models	medium	Ranked #7 in Decision models on same-GPU latency. Sieve 31B is inside the field.

Embed

Badges for the leaders

Bobcat 1.3 (31B)

[![SOTA · Decision models · Oct 2026](https://isitsota.com/badge/bobcat-1-3/decision.svg?slice=latency)](https://isitsota.com/m/bobcat-1-3)

Display only

Self-reported claims

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

Best page and recent changes

Best AI model for decision models

What is a decision model

Evidence recipe

What can move this crown

Decision Index Full — primary, weight 1
JevBench — primary, weight 1
Decision Index latency — display, weight 0 (display only, cannot crown)
JevBench price — display, weight 0 (display only, cannot crown)
Vendor decision claims — display, weight 0 (display only, cannot crown)

Who is SOTA in Decision models?

As of Oct 14, 2026, Bobcat 1.3 (31B) is state of the art in Decision models (since Oct 14, 2026; sources Decision Index latency; methodology v1.0).

Since when is the Decision models crown current?

The current crown in Decision models has held since Oct 14, 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.