Is Sieve 31B v3 SOTA in Decision models?Near-SOTA · Decision modelsClose in Decision models: rank #12, 3.2 percentile points behind the leader.
How it scores here
Sieve 31B v3 in Decision models
Primary benchmarks
- Decision Index Full: 71.1 (CI 70.6–71.6) on Nov 21, 2026 (#15 of 420).
On the category's weighted score it is 3.2 points behind #1 karpo-decision-31B and 0.3 behind the next model up, munku (Gemma 4 31B).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 9 | Copernicus-57B | 97.7 |
| 10 | FlexDM-LoRA 2.1 · Gemma-4-31B | 97.4 |
| 11 | munku (Gemma 4 31B) | 97.1 |
| 12 | Sieve 31B v3 | 96.8 |
| 13 | OneJev1.6g-31B | 96.5 |
| 14 | Turion Jev 31B | 96.2 |
| 15 | eshbar-lulilla (Gemma 4 31B) | 95.7 |
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 |