Is karpo-decision-31B state of the art?Yes.SOTA in Decision models (tied).
As of Nov 22, 2026, karpo-decision-31B is tied for state of the art with low confidence in Decision models (since Nov 11, 2026; sources Decision Index Full; methodology v1.0). karpo-decision-31B is co-SOTA in Decision models with low confidence because primary sources disagree beyond the margin of error (with GLiDE 27B, kudhab (Gemma 4 31B), Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)).
Facts and scores
karpo-decision-31B is an open-weights text model from MachinePulse; 31B parameters and no public price.
How it scores
- On Decision Index Full it scores 73.9 (CI 73.4–74.4), #1 of 420 (top 1%); GLiDE 27B is 0.5 below.
- On Decision Index Brier it scores 23.9%, #5 of 419 (top 2%); 3.5 pts behind lg-decision-4B; level with StartLux-Decision v1.1 27B above and Strands Decider v2 31B is 0.2 pts below.
- On Decision Index ECE it scores 4.8%, #135 of 420 (top 33%); 3.7 pts behind KnowLine 9B Gen2; level with AJev lora1 (Gemma 4 26B-A4B) above and level with munku (Gemma 4 31B) below.
History
First result on isitsota: Nov 21, 2026. Best overall rank so far: #1 in Decision models, first held Nov 11, 2026. Crown intervals: Decision models Nov 11, 2026–Nov 12, 2026, Decision models Nov 12, 2026–Nov 21, 2026 and Decision models Nov 21, 2026–now.
Reliability
Index bins for karpo-decision-31B. Confidence on the horizontal axis, accuracy on the vertical axis.
Median 94.3 ms, same GPU.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full karpo-decision-31B | 73.9 73.4–74.4 | 2026-11-21 | INDEP. | snap_decision-index_2026-11-21_release-v4|decision-index-0.4.1 |
Where it sits in the succession
Related pages
- Decision models
- 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)
- karpo-decision-31B vs Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)
- karpo-decision-31B vs REAX 1.3
- karpo-decision-31B vs Logits Sigma-1 Duo
- Decision Index Full
- Decision Index latency
- Lab: MachinePulse
- Crown change in November 2026 recap
Is karpo-decision-31B SOTA?
As of Nov 22, 2026, karpo-decision-31B is tied for state of the art with low confidence in Decision models (since Nov 11, 2026; sources Decision Index Full; methodology v1.0).
What is karpo-decision-31B best at?
As of Nov 22, 2026, karpo-decision-31B is tied for state of the art with low confidence in Decision models (since Nov 11, 2026; sources Decision Index Full).
How does karpo-decision-31B rank in Decision models?
Best current rank: #1 in Decision models, as of Nov 22, 2026.
When was karpo-decision-31B last SOTA?
As of Nov 22, 2026, karpo-decision-31B last held Decision models from Nov 11, 2026 until Nov 12, 2026.