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.
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.
Reliability
Index bins for Sieve 31B v3. Confidence on the horizontal axis, accuracy on the vertical axis.
Median 231.8 ms, same GPU.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full Sieve 31B v3 | 71.1 70.6–71.6 | 2026-11-21 | INDEP. | snap_decision-index_2026-11-21_release-v4|decision-index-0.4.1 |
Where it sits in the succession
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| Decision models | Near-SOTA | #12 | karpo-decision-31B |
Related pages
- Decision models
- Compare with the current leader in Decision models: karpo-decision-31B
- Compare with the current leader in Decision models: Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
- Compare with the current leader in Decision models: GLiDE 27B
- Compare with the current leader in Decision models: kudhab (Gemma 4 31B)
- Sieve 31B v3 vs Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)
- Sieve 31B v3 vs REAX 1.3
- Sieve 31B v3 vs Logits Sigma-1 Duo
- Decision Index Full
- Lab: Sthānika AI
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.