Sign in
VERIFIEDNov 222026

Is Saif 0.8 Lightening v0.1 (0.8B) state of the art?Unranked.#103 on Decision Index latency; missing Decision Index Full and JevBench

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

Computed automaticallyas of Nov 22, 2026methodology v1.0confidence: low
View as of point-in-time crowns
At a glance

Facts and scores

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.

Calibration

Reliability

Index bins for Saif 0.8 Lightening v0.1 (0.8B). Confidence on the horizontal axis, accuracy on the vertical axis.

Median 52.7 ms, same GPU.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
Decision Index latency
Saif 0.8 Lightening v0.1 (0.8B)
52.72026-11-06INDEP.snap_decision-index_2026-11-06_release-v4|decision-index-0.4.1
Reign history

Where it sits in the succession

Full timeline →

Crown intervals for this model are still empty.

Honest about the gaps

Where it is not the crown

CategoryThis modelRankLeader
Decision modelsNot enough data—karpo-decision-31B
Links

Related pages

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).

What is Saif 0.8 Lightening v0.1 (0.8B) best at?

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).