VERIFIEDNov 222026
Is crystal-0.8b state of the art?#327Best current rank: #327 in Decision models, as of Nov 22, 2026.
As of Nov 22, 2026, crystal-0.8b is ranked #327 in Decision models (since Nov 22, 2026; sources Decision Index Full; methodology v1.0). Ranked #327 in Decision models.
At a glance
Facts and scores
crystal-0.8b is an open-weights text model from Unknown; 0.9B parameters and no public price.
How it scores
- On Decision Index ECE it scores 1.7%, #12 of 420 (top 3%); 0.6 pts behind KnowLine 9B Gen2; level with GLiDE 9B above and REAX 1.3 is 0.1 pts below.
- On Decision Index latency it scores 53.8, #175 of 419 (top 42%); 23.8 behind Prumo; vLLM-SR d3-flash (9B) is 0.1 above and Aplomb 1 (5.3B decision model on Qwen3.5-4B, trained readout head, self-hosted) is 0.1 below.
- On Decision Index Brier it scores 44.1%, #269 of 419 (top 65%); 23.7 pts behind lg-decision-4B; level with Sieve 9B above and LatentMesh Blitz 2B v1 is 0.1 pts below.
History
First result on isitsota: Nov 21, 2026. Best overall rank so far: #327 in Decision models, first held Nov 22, 2026.
Calibration
Reliability
Index bins for crystal-0.8b. Confidence on the horizontal axis, accuracy on the vertical axis.
Median 53.8 ms, same GPU.
Receipts
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full crystal-0.8b | 29.4 28.9–29.9 | 2026-11-21 | INDEP. | snap_decision-index_2026-11-21_release-v4|decision-index-0.4.1 |
Reign history
Where it sits in the succession
Crown intervals for this model are still empty.
Honest about the gaps
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| Decision models | #327 in this category | #327 | karpo-decision-31B |
Links
Related pages
Is crystal-0.8b SOTA?
Best current rank: #327 in Decision models, as of Nov 22, 2026.
What is crystal-0.8b best at?
As of Nov 22, 2026, crystal-0.8b is ranked #327 in Decision models (since Nov 22, 2026; sources Decision Index Full).