Is Valen-Decision 1.5 27B SOTA in Decision models?#71 in Decision modelsRanked #71 in Decision models.
How it scores here
Valen-Decision 1.5 27B in Decision models
Primary benchmarks
- Decision Index Full: 65.2 (CI 64.7–65.7) on Nov 21, 2026 (#68 of 420).
On the category's weighted score it is 15.7 points behind #1 karpo-decision-31B and 0.3 behind the next model up, OneShot 27B.
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 68 | KnowLine 35B-A3B Gen1.5 | 84.9 |
| 69 | torchcast-decision-12b (Torchcast AI, Gemma-4-12B fine-tune, option-letter logprob readout) | 84.8 |
| 70 | OneShot 27B | 84.6 |
| 71 | Valen-Decision 1.5 27B | 84.3 |
| 72 | AutoJev-27B (denis-pplx, Qwen3.8-27B) | 84.1 |
| 73 | Bobcat 1.3 (31B) | 84.1 |
| 74 | Amos 1 Large (27B) | 83.8 |
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 |