# Is Copernicus-57B SOTA?

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.

Canonical: https://isitsota.com/m/copernicus-57b-fla/decision
Last updated: 2026-11-21
Methodology v1.0. Computed automatically.

- Decision models: Near-SOTA · Decision models — Close in Decision models: rank #9, 2.3 percentile points behind the leader.

## Decision models

https://isitsota.com/c/decision

### Primary benchmarks

- Decision Index Full: 71.8 (CI 71.3–72.3) on Nov 21, 2026 (#11 of 420).

On the category's weighted score it is 2.3 points behind #1 karpo-decision-31B and 0.0 behind the next model up, decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted).

### Nearby on the board

| # | Model | Category score |
| ---: | --- | ---: |
| 6 | [Strands Decider v2 31B](https://isitsota.com/m/strands-decider-v2-31b.md) | 98.3 |
| 7 | [Copernicus-31B](https://isitsota.com/m/copernicus-31b.md) | 98.0 |
| 8 | [decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted)](https://isitsota.com/m/decisio-gemma-4-31b-v080.md) | 97.7 |
| 9 | **Copernicus-57B** | 97.7 |
| 10 | [FlexDM-LoRA 2.1 · Gemma-4-31B](https://isitsota.com/m/flexdm-lora-2-1-gemma-4-31b.md) | 97.4 |
| 11 | [munku (Gemma 4 31B)](https://isitsota.com/m/munku.md) | 97.1 |
| 12 | [Sieve 31B v3](https://isitsota.com/m/sieve-31b-v3.md) | 96.8 |

## Related

- Model page: https://isitsota.com/m/copernicus-57b-fla.md
- Lab: [Poindexter Labs](https://isitsota.com/labs/poindexter-labs.md)
- Category: [Decision models](https://isitsota.com/c/decision.md)
- JSON: https://api.isitsota.com/v1/models/copernicus-57b-fla
