# Is JevK5 v0.3 (4B) SOTA?

Best current rank: #158 in Decision models, as of Nov 22, 2026.

As of Nov 22, 2026, JevK5 v0.3 (4B) is ranked #158 in Decision models (since Nov 22, 2026; sources JevBench; methodology v1.0). Ranked #158 in Decision models.

Canonical: https://isitsota.com/m/jevk5-v0-3-4b
Last updated: 2026-10-08
Methodology v1.0. Computed automatically.

- Decision models: #158 in Decision models — Ranked #158 in Decision models.

## At a glance

JevK5 v0.3 (4B) is a closed-weights text model from Unknown; 4B parameters and no public price.

### How it scores

- On JevBench it scores 64.2 (CI 63.7–64.7), #49 of 134 (top 37%); 18.6 behind Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout); decider-4b v2 (Mapika) is 0.7 above and Clef-Flash (Cloudflare, Qwen3.5-9B post-train with a joint schema head, multimodal, measured on text) is 0.4 below.
- On JevBench price it scores 1.7%, #49 of 134 (top 37%); 1.6 pts behind verdict-small (Manavarya09, multilingual-e5-small 118M); level with Plumb-4B (crh225, JevK5 v0.2 + LoRA) above and level with JevK5 v0.2.0 below.

### History

First result on isitsota: Oct 8, 2026. Best overall rank so far: #158 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/jevk5-v0-3-4b
