# Is JPT-35B-A3B (Qwen3.5-35B-A3B fine-tune) SOTA?

Best current rank: #128 in Decision models, as of Nov 22, 2026.

As of Nov 22, 2026, JPT-35B-A3B (Qwen3.5-35B-A3B fine-tune) is ranked #128 in Decision models (since Nov 22, 2026; sources Decision Index Full and JevBench; methodology v1.0). Ranked #128 in Decision models.

Canonical: https://isitsota.com/m/jpt-35b-a3b
Last updated: 2026-11-21
Methodology v1.0. Computed automatically.

- Decision models: #128 in Decision models — Ranked #128 in Decision models.

## At a glance

JPT-35B-A3B (Qwen3.5-35B-A3B fine-tune) is an open-weights (cc-by-nc-4.0) text model from Unknown; 36B parameters and no public price.

### How it scores

- On JevBench it scores 70.7 (CI 70.2–71.2), #30 of 134 (top 23%); 12.1 behind Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout); level with decisio v0.8.0 on gemma-4-12B-it (frozen, one forward pass, self-hosted) above and decider chat on Gemma-4-31B-it (Mapika, frozen base, inference technique) is 0.1 below.
- On Decision Index ECE it scores 4.9%, #144 of 420 (top 35%); 3.8 pts behind KnowLine 9B Gen2; level with RSI-Jev v6.1 VL 4B above and level with Adjudex-4B v7 below.
- On Decision Index Full it scores 54.1 (CI 53.6–54.6), #158 of 420 (top 38%); 19.8 behind karpo-decision-31B; vLLM-SR d3-flash (9B) is 0.2 above and chinese-decision-pointer-4b is 0.1 below.

### History

First result on isitsota: Oct 8, 2026. Best overall rank so far: #128 in Decision models, first held Nov 22, 2026.


## Related

- Lab: [Unknown](https://isitsota.com/labs/unknown.md)
- Category: [Decision models](https://isitsota.com/c/decision.md)
- JSON: https://api.isitsota.com/v1/models/jpt-35b-a3b
