Is Crivo-68M SOTA in Decision models?#380 in Decision modelsRanked #380 in Decision models.
How it scores here
Crivo-68M in Decision models
Primary benchmarks
- Decision Index Full: 19.5 (CI 19.0–20.0) on Nov 21, 2026 (#361 of 420).
On the category's weighted score it is 84.3 points behind #1 karpo-decision-31B and 0.3 behind the next model up, WaterSheep (Samrat Dutta, ModernBERT-base encoder with calibrated heads, served by the author's own `watersheep --serve`).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 377 | Sieve 0.8B | 16.5 |
| 378 | tasksource Decider nano v5 (150M) | 15.9 |
| 379 | WaterSheep (Samrat Dutta, ModernBERT-base encoder with calibrated heads, served by the author's own `watersheep --serve`) | 15.9 |
| 380 | Crivo-68M | 15.7 |
| 381 | Amber 68M | 15.4 |
| 382 | open-jev-deberta-v3-large (local CPU) | 15.2 |
| 383 | ClassOne Qwen3.5 2B | 15.1 |
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 |