Is crystal-0.8b SOTA in Decision models?#327 in Decision modelsRanked #327 in Decision models.
How it scores here
crystal-0.8b in Decision models
Primary benchmarks
- Decision Index Full: 29.4 (CI 28.9–29.9) on Nov 21, 2026 (#313 of 420).
On the category's weighted score it is 73.3 points behind #1 karpo-decision-31B and 0.3 behind the next model up, OneJev1.6-0.8B.
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 324 | kev 4B (research preview) | 27.3 |
| 325 | Diorite G4 E2B v1.0 | 27.2 |
| 326 | OneJev1.6-0.8B | 27.0 |
| 327 | crystal-0.8b | 26.7 |
| 328 | Mixedbread mxbai-rerank-base-v2 | 26.5 |
| 329 | MoDe-L | 26.4 |
| 330 | vLLM-SR vela3-fast (Vela 3.0, 0.4B) | 26.1 |
Standings
Decision models
| # | Model | State |
|---|---|---|
| 1 | karpo-decision-31B | Co-SOTA |
| 1 | Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) | Co-SOTA |
| 1 | GLiDE 27B | Co-SOTA |
| 1 | kudhab (Gemma 4 31B) | Co-SOTA |
| 2 | Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits) | Near-SOTA |
| 3 | REAX 1.3 | Near-SOTA |
| 4 | Logits Sigma-1 Duo | Near-SOTA |
| 5 | KnowLine 31B Gen2 | Near-SOTA |
| 6 | Strands Decider v2 31B | Near-SOTA |
| 7 | Copernicus-31B | Near-SOTA |
| 8 | decisio v0.8.0 on gemma-4-31B-it (frozen, FP8 on load, one prefill per state, self-hosted) | Near-SOTA |
| 9 | Copernicus-57B | Near-SOTA |