Is vLLM-SR d3-ultra (Decision 3.0, 27B) state of the art?#17Best current rank: #17 in Decision models, as of Nov 22, 2026.
As of Nov 22, 2026, vLLM-SR d3-ultra (Decision 3.0, 27B) is ranked #17 in Decision models (since Nov 22, 2026; sources Decision Index Full; methodology v1.0). Ranked #17 in Decision models.
Facts and scores
vLLM-SR d3-ultra (Decision 3.0, 27B) is an open-weights text model from vLLM Semantic Router; 26B parameters and no public price.
How it scores
- On Decision Index Full it scores 70.2 (CI 69.7–70.7), #20 of 420 (top 5%); 3.7 behind karpo-decision-31B; Jeffan-27B-1211 is 0.1 above and Bespoke Nimble v4.1 Max (27B) is 0.2 below.
- On Decision Index Brier it scores 27.3%, #41 of 419 (top 10%); 6.9 pts behind lg-decision-4B; level with WeMM-JEV-27B above and level with Adjudex-4B v7 below.
- On Decision Index ECE it scores 6.7%, #211 of 420 (top 51%); 5.6 pts behind KnowLine 9B Gen2; GLiDE 2B is 0.1 pts above and level with AutoTrust-JEV-27B v1.1 below.
History
First result on isitsota: Nov 21, 2026. Best overall rank so far: #17 in Decision models, first held Nov 22, 2026.
Reliability
Index bins for vLLM-SR d3-ultra (Decision 3.0, 27B). Confidence on the horizontal axis, accuracy on the vertical axis.
Median 200.5 ms, same GPU.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full vLLM-SR d3-ultra (Decision 3.0, 27B) | 70.2 69.7–70.7 | 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 | #17 in this category | #17 | 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)
- vLLM-SR d3-ultra (Decision 3.0, 27B) vs Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)
- vLLM-SR d3-ultra (Decision 3.0, 27B) vs REAX 1.3
- vLLM-SR d3-ultra (Decision 3.0, 27B) vs Logits Sigma-1 Duo
- Decision Index Full
- Lab: vLLM Semantic Router
Is vLLM-SR d3-ultra (Decision 3.0, 27B) SOTA?
Best current rank: #17 in Decision models, as of Nov 22, 2026.
What is vLLM-SR d3-ultra (Decision 3.0, 27B) best at?
As of Nov 22, 2026, vLLM-SR d3-ultra (Decision 3.0, 27B) is ranked #17 in Decision models (since Nov 22, 2026; sources Decision Index Full).