# Is Saif 0.8 Lightening v0.1 (0.8B) SOTA?

As of Nov 22, 2026, Saif 0.8 Lightening v0.1 (0.8B) is short of the evidence for a rank in Decision models (since Nov 22, 2026; sources Decision Index latency; methodology v1.0). #103 on Decision Index latency; missing Decision Index Full and JevBench

Canonical: https://isitsota.com/m/saif-0-8-lightening
Last updated: 2026-11-06
Methodology v1.0. Computed automatically.

- Decision models: Not enough data — #103 on Decision Index latency; missing Decision Index Full and JevBench

## At a glance

Saif 0.8 Lightening v0.1 (0.8B) is an open-weights text model from Gyr Technology; 0.8B parameters and no public price.

### How it scores

- On Decision Index latency it scores 52.7, #164 of 419 (top 40%); 22.7 behind Prumo; Nirnaya Turbo 1.0 is 0.1 above and Starlord 4B Preview is 0.1 below.
- On Decision Index Brier it scores 45.0%, #279 of 419 (top 67%); 24.6 pts behind lg-decision-4B; Hopper 12B trained (gemma-4-12B-it frozen + LoRA r32 unmerged, one forward pass, self-hosted) is 0.1 pts above and level with Aplomb 1 (5.3B decision model on Qwen3.5-4B, trained readout head, self-hosted) below.
- On Decision Index ECE it scores 9.3%, #292 of 420 (top 70%); 8.2 pts behind KnowLine 9B Gen2; level with MoDe-M above and vLLM-SR d3-lite (0.8B) is 0.1 pts below.

### History

First result on isitsota: Nov 6, 2026.


## Related

- Lab: [Gyr Technology](https://isitsota.com/labs/gyr-technology.md)
- Category: [Decision models](https://isitsota.com/c/decision.md)
- JSON: https://api.isitsota.com/v1/models/saif-0-8-lightening
