Sign in
VERIFIEDNov 222026

Is Sieve 31B v3 state of the art?Close.Near-SOTA in Decision models, rank #12.

As of Nov 22, 2026, Sieve 31B v3 is near state of the art, rank #12 in Decision models (since Nov 22, 2026; sources Decision Index Full; methodology v1.0). Close in Decision models: rank #12, 3.2 percentile points behind the leader.

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

Facts and scores

Sieve 31B v3 is an open-weights text model from Sthānika AI; 31B parameters and no public price.

How it scores

  • On Decision Index Full it scores 71.1 (CI 70.6–71.6), #15 of 420 (top 4%); 2.8 behind karpo-decision-31B; munku (Gemma 4 31B) is 0.2 above and OneJev1.6g-31B is 0.2 below.
  • On Decision Index Brier it scores 26.7%, #32 of 419 (top 8%); 6.3 pts behind lg-decision-4B; level with KnowLine 9B Gen2 above and vera-large-2o is 0.2 pts below.
  • On Decision Index ECE it scores 5.4%, #166 of 420 (top 40%); 4.3 pts behind KnowLine 9B Gen2; level with Standard One 35B SH (v1) above and level with vLLM-SR d3-turbo (27B) below.

History

First result on isitsota: Nov 21, 2026. Best overall rank so far: #1 in Decision models, first held Oct 28, 2026. Crown intervals: Decision models Oct 28, 2026–Nov 6, 2026.

Calibration

Reliability

Index bins for Sieve 31B v3. Confidence on the horizontal axis, accuracy on the vertical axis.

Median 231.8 ms, same GPU.

Receipts

Evidence

Scores come from the latest ingested snapshot
SourceScoreDateTypeReceipt
Decision Index Full
Sieve 31B v3
71.1 70.6–71.62026-11-21INDEP.snap_decision-index_2026-11-21_release-v4|decision-index-0.4.1
Reign history

Where it sits in the succession

Full timeline →
Decision models
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
MISA AI 2.0 Decision Plus · oak (31B)
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
vLLM-SR d3 (27B)
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
StartLux-Decision v1.1 27B
baselabs mammoth-1 (27B)
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
Fastino GLiDE 1.2
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
Fastino GLiDE 1.2
KnowLine 31B Gen1
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
Sieve 31B v3
GLiDE 27B
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
REAX 1.3
GLiDE 27B
karpo-decision-31B
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
REAX 1.3
GLiDE 27B
karpo-decision-31B
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
GLiDE 27B
karpo-decision-31B
kudhab (Gemma 4 31B)
Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
Honest about the gaps

Where it is not the crown

CategoryThis modelRankLeader
Decision modelsNear-SOTA#12karpo-decision-31B
Links

Related pages

Is Sieve 31B v3 SOTA?

As of Nov 22, 2026, Sieve 31B v3 is near state of the art, rank #12 in Decision models (since Nov 22, 2026; sources Decision Index Full; methodology v1.0).

What is Sieve 31B v3 best at?

As of Nov 22, 2026, Sieve 31B v3 is near state of the art, rank #12 in Decision models (since Nov 22, 2026; sources Decision Index Full).

How does Sieve 31B v3 rank in Decision models?

Best current rank: #12 in Decision models, as of Nov 22, 2026.

When was Sieve 31B v3 last SOTA?

As of Nov 22, 2026, Sieve 31B v3 last held Decision models from Oct 28, 2026 until Nov 6, 2026.