Is Sloth-27B v1 SOTA in Decision models?#64 in Decision modelsRanked #64 in Decision models.
How it scores here
Sloth-27B v1 in Decision models
Primary benchmarks
- Decision Index Full: 66.2 (CI 65.7–66.7) on Nov 21, 2026 (#61 of 420).
On the category's weighted score it is 14.2 points behind #1 karpo-decision-31B and 0.2 behind the next model up, Kev 27B (Kev 1.0, Qwen3.8-27B).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 61 | Mercury Decide (Inception; System One decisions API, served free on OpenRouter as inception/mercury-decide:free) | 86.4 |
| 62 | vera-large-2o | 86.1 |
| 63 | Kev 27B (Kev 1.0, Qwen3.8-27B) | 86.0 |
| 64 | Sloth-27B v1 | 85.8 |
| 65 | swanOne (blockbrain, Qwen3.8-Flash-Next NVFP4) | 85.6 |
| 66 | Decider 31B (NVFP4) | 85.5 |
| 67 | Diorite G4 31B v1.0 | 85.2 |
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 |