Is GLiDE 27B state of the art?Yes.SOTA in Decision models (tied).
As of Nov 22, 2026, GLiDE 27B is tied for state of the art with low confidence in Decision models (since Nov 6, 2026; sources Decision Index Full; methodology v1.0). GLiDE 27B is co-SOTA in Decision models with low confidence because primary sources disagree beyond the margin of error (with karpo-decision-31B, kudhab (Gemma 4 31B), Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)).
Facts and scores
GLiDE 27B is an open-weights text model from Fastino; 26B parameters and no public price.
How it scores
- On Decision Index Full it scores 73.4 (CI 72.9–73.9), #2 of 420 (top 1%); 0.5 behind karpo-decision-31B; karpo-decision-31B is 0.5 above and kudhab (Gemma 4 31B) is 0.4 below.
- On Decision Index Brier it scores 25.1%, #16 of 419 (top 4%); 4.7 pts behind lg-decision-4B; Jeffan-31b-1710 is 0.2 pts above and level with KnowLine 35B-A3B Gen1.5 below.
- On Decision Index ECE it scores 2.1%, #24 of 420 (top 6%); 1.0 pts behind KnowLine 9B Gen2; level with Decider chat · Qwen3.6-27B above and level with KnowLine 31B Gen2 below.
History
First result on isitsota: Nov 21, 2026. Best overall rank so far: #1 in Decision models, first held Nov 6, 2026. Crown intervals: Decision models Nov 6, 2026–Nov 11, 2026, 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 GLiDE 27B. Confidence on the horizontal axis, accuracy on the vertical axis.
Median 122.4 ms, same GPU.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full GLiDE 27B | 73.4 72.9–73.9 | 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: 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: kudhab (Gemma 4 31B)
- GLiDE 27B vs Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)
- GLiDE 27B vs REAX 1.3
- GLiDE 27B vs Logits Sigma-1 Duo
- Decision Index Full
- Decision Index ECE
- Decision Index latency
- Lab: Fastino
- Crown change in November 2026 recap
Is GLiDE 27B SOTA?
As of Nov 22, 2026, GLiDE 27B is tied for state of the art with low confidence in Decision models (since Nov 6, 2026; sources Decision Index Full; methodology v1.0).
What is GLiDE 27B best at?
As of Nov 22, 2026, GLiDE 27B is tied for state of the art with low confidence in Decision models (since Nov 6, 2026; sources Decision Index Full).
How does GLiDE 27B rank in Decision models?
Best current rank: #1 in Decision models, as of Nov 22, 2026.
When was GLiDE 27B last SOTA?
As of Nov 22, 2026, GLiDE 27B last held Decision models from Nov 6, 2026 until Nov 11, 2026.