# Is Raw Phi-4 mini direct logits SOTA?

Best current rank: #386 in Decision models, as of Nov 22, 2026.

As of Nov 22, 2026, Raw Phi-4 mini direct logits is ranked #386 in Decision models (since Nov 22, 2026; sources JevBench; methodology v1.0). Ranked #386 in Decision models.

Canonical: https://isitsota.com/m/raw-phi-4-mini
Last updated: 2026-10-08
Methodology v1.0. Computed automatically.

- Decision models: #386 in Decision models — Ranked #386 in Decision models.

## At a glance

Raw Phi-4 mini direct logits is an open-weights (MIT) text model from Microsoft; no public parameter count and no public price.

### How it scores

- On JevBench price it scores 3.6%, #81 of 134 (top 61%); 3.5 pts behind verdict-small (Manavarya09, multilingual-e5-small 118M); Jev 1.13.0 (TypeSafe AI) is 0.4 pts above and SPX-CD Flash (SurdAI, hosted /v1/systemone, Oct-4 checkpoint) is 0.3 pts below.
- On JevBench it scores 35.3 (CI 34.8–35.8), #115 of 134 (top 86%); 47.5 behind Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout); open-jev-deberta-v3-large (local CPU) is 0.1 above and Raw Qwen3 4B Instruct 2507 direct logits is 0.7 below.

### History

First result on isitsota: Oct 8, 2026. Best overall rank so far: #386 in Decision models, first held Nov 22, 2026.


## Related

- Lab: [Microsoft](https://isitsota.com/labs/microsoft.md)
- Category: [Decision models](https://isitsota.com/c/decision.md)
- JSON: https://api.isitsota.com/v1/models/raw-phi-4-mini
