# Is FlexDM-LoRA 2.1 · Gemma-4-31B SOTA?

Near-SOTA in Decision models, rank #10.

As of Nov 22, 2026, FlexDM-LoRA 2.1 · Gemma-4-31B is near state of the art, rank #10 in Decision models (since Nov 22, 2026; sources Decision Index Full; methodology v1.0). Close in Decision models: rank #10, 2.6 percentile points behind the leader.

Canonical: https://isitsota.com/m/flexdm-lora-2-1-gemma-4-31b
Last updated: 2026-11-21
Methodology v1.0. Computed automatically.

- Decision models: Near-SOTA · Decision models — Close in Decision models: rank #10, 2.6 percentile points behind the leader.

## At a glance

FlexDM-LoRA 2.1 · Gemma-4-31B is an open-weights text model from Unknown; 31B parameters and no public price.

### How it scores

- On Decision Index Full it scores 71.6 (CI 71.1–72.1), #12 of 420 (top 3%); 2.3 behind karpo-decision-31B; Copernicus-57B is 0.2 above and Fastino GLiDE 1.2 is 0.1 below.
- On Decision Index Brier it scores 30.5%, #87 of 419 (top 21%); 10.1 pts behind lg-decision-4B; level with OneJev1.6-4B above and Darwin-27B-RSI-Decision is 0.1 pts below.
- On Decision Index ECE it scores 5.4%, #164 of 420 (top 40%); 4.3 pts behind KnowLine 9B Gen2; level with liquamen (Gemma 4 31B) above and level with Standard One 35B SH (v1) below.

### History

First result on isitsota: Nov 21, 2026. Best overall rank so far: #10 in Decision models, first held Nov 22, 2026.


## Related

- Lab: [Unknown](https://isitsota.com/labs/unknown.md)
- Category: [Decision models](https://isitsota.com/c/decision.md)
- [Compare with the current leader in Decision models: karpo-decision-31B](https://isitsota.com/compare/flexdm-lora-2-1-gemma-4-31b-vs-karpo-decision-31b.md)
- [Compare with the current leader in Decision models: Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)](https://isitsota.com/compare/flexdm-lora-2-1-gemma-4-31b-vs-pplx-decider-v1-1-27b.md)
- [Compare with the current leader in Decision models: GLiDE 27B](https://isitsota.com/compare/flexdm-lora-2-1-gemma-4-31b-vs-glide-v1-2-1-loop.md)
- [Compare with the current leader in Decision models: kudhab (Gemma 4 31B)](https://isitsota.com/compare/flexdm-lora-2-1-gemma-4-31b-vs-kudhab.md)
- [FlexDM-LoRA 2.1 · Gemma-4-31B vs Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)](https://isitsota.com/compare/flexdm-lora-2-1-gemma-4-31b-vs-quyet-1-0-large.md)
- [FlexDM-LoRA 2.1 · Gemma-4-31B vs REAX 1.3](https://isitsota.com/compare/flexdm-lora-2-1-gemma-4-31b-vs-reax-1-3.md)
- [FlexDM-LoRA 2.1 · Gemma-4-31B vs Logits Sigma-1 Duo](https://isitsota.com/compare/flexdm-lora-2-1-gemma-4-31b-vs-logits-sigma-1-duo.md)
- JSON: https://api.isitsota.com/v1/models/flexdm-lora-2-1-gemma-4-31b
