Is Bespoke Nimble v4.1 Max (27B) SOTA in Decision models?#18 in Decision modelsRanked #18 in Decision models.
How it scores here
Bespoke Nimble v4.1 Max (27B) in Decision models
Primary benchmarks
- Decision Index Full: 70.0 (CI 69.5–70.5) on Nov 21, 2026 (#21 of 420).
On the category's weighted score it is 4.9 points behind #1 karpo-decision-31B and 0.3 behind the next model up, vLLM-SR d3-ultra (Decision 3.0, 27B).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 15 | Jeffan-27B-1211 | 95.7 |
| 16 | Eikos-27B (caiovicentino1, Qwen3.8-27B) | 95.5 |
| 17 | vLLM-SR d3-ultra (Decision 3.0, 27B) | 95.4 |
| 18 | Bespoke Nimble v4.1 Max (27B) | 95.1 |
| 19 | H2O Lightning 31B v1.3.0 | 94.8 |
| 20 | René-1 31B FP8 (salfatigroup, Gemma 4 31B full fine-tune, one-pass option readout) | 94.7 |
| 21 | Jeffan-31b-1710 | 94.5 |
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 |