# Is Raw Qwen3 0.6B direct logits SOTA?

Best current rank: #448 in Decision models, as of Nov 22, 2026.

As of Nov 22, 2026, Raw Qwen3 0.6B direct logits is ranked #448 in Decision models (since Nov 22, 2026; sources JevBench; methodology v1.0). Ranked #448 in Decision models.

Canonical: https://isitsota.com/m/raw-qwen3-0-6b
Last updated: 2026-10-08
Methodology v1.0. Computed automatically.

- Decision models: #448 in Decision models — Ranked #448 in Decision models.

## At a glance

Raw Qwen3 0.6B direct logits is an open-weights (Apache-2.0) text model from Alibaba / Qwen; 0.6B parameters and no public price.

### How it scores

- On JevBench price it scores 0.6%, #22 of 134 (top 17%); 0.5 pts behind verdict-small (Manavarya09, multilingual-e5-small 118M); level with open-jev-deberta-v3-large (local CPU) above and SimpleJev (Qwen3.5-0.8B, CPU) is 0.4 pts below.
- On JevBench it scores 8.2 (CI 7.7–8.7), #133 of 134 (top 100%); 74.6 behind Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout); Raw Qwen3 1.7B direct logits is 0.1 above and Fastino GLiNER-2.5-Decide (hosted API) is 26.1 below.

### History

First result on isitsota: Oct 8, 2026. Best overall rank so far: #448 in Decision models, first held Nov 22, 2026.


## Related

- Lab: [Alibaba / Qwen](https://isitsota.com/labs/alibaba.md)
- Category: [Decision models](https://isitsota.com/c/decision.md)
- JSON: https://api.isitsota.com/v1/models/raw-qwen3-0-6b
