Is Copernicus-57B state of the art?Yes.Yes on Decision models (calibration). Not the overall leader.
As of Nov 22, 2026, Copernicus-57B is state of the art in Decision models (since Nov 17, 2026; sources Decision Index ECE; methodology v1.0). Copernicus-57B leads Decision models calibration since 2026-11-17, with the lowest ECE in the top quartile of accuracy.
Facts and scores
Copernicus-57B is an open-weights text model from Poindexter Labs; 57B parameters and no public price.
How it scores
- On Decision Index ECE it scores 1.4%, #6 of 420 (top 2%); 0.3 pts behind KnowLine 9B Gen2; level with Strands Decider v2 E2B above and level with KnowLine 12B Gen1 below.
- On Decision Index Brier it scores 24.1%, #7 of 419 (top 2%); 3.7 pts behind lg-decision-4B; level with Strands Decider v2 31B above and Ainvest-Decision-27B v1.0 is 0.2 pts below.
- On Decision Index Full it scores 71.8 (CI 71.3–72.3), #11 of 420 (top 3%); 2.1 behind karpo-decision-31B; KnowLine 31B Gen1 is 0.1 above and FlexDM-LoRA 2.1 · Gemma-4-31B is 0.2 below.
History
First result on isitsota: Nov 21, 2026. Best overall rank so far: #9 in Decision models, first held Nov 22, 2026.
The ruling, in plain English
Close in Decision models: rank #9, 2.3 percentile points behind the leader.
Reliability
Index bins for Copernicus-57B. Confidence on the horizontal axis, accuracy on the vertical axis.
Median 248.7 ms, same GPU.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full Copernicus-57B | 71.8 71.3–72.3 | 2026-11-21 | INDEP. | snap_decision-index_2026-11-21_release-v4|decision-index-0.4.1 |
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| Decision models | Near-SOTA | #9 | 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)
- Copernicus-57B vs Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)
- Copernicus-57B vs REAX 1.3
- Copernicus-57B vs Logits Sigma-1 Duo
- Decision Index Full
- Decision Index ECE
- Lab: Poindexter Labs
- Crown change in November 2026 recap
Is Copernicus-57B SOTA?
As of Nov 22, 2026, Copernicus-57B is state of the art in Decision models (since Nov 17, 2026; sources Decision Index ECE; methodology v1.0).
What is Copernicus-57B best at?
As of Nov 22, 2026, Copernicus-57B is near state of the art, rank #9 in Decision models (since Nov 22, 2026; sources Decision Index Full).
How does Copernicus-57B rank in Decision models?
Best current rank: #9 in Decision models, as of Nov 22, 2026.