Is decisio 0.4.0 (Qwen3.6-35B-A3B) SOTA in Decision models?#189 in Decision modelsRanked #189 in Decision models.
How it scores here
decisio 0.4.0 (Qwen3.6-35B-A3B) in Decision models
Primary benchmarks
- Decision Index Full: 50.8 (CI 50.3–51.3) on Nov 21, 2026 (#182 of 420).
On the category's weighted score it is 42.3 points behind #1 karpo-decision-31B and 0.3 behind the next model up, frontier-infra Jebadiah 9B v2.1 (t1e).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 186 | Open-Jev 9B (Zefan Cai) | 58.3 |
| 187 | Bespoke Nimble 9B v3 | 58.3 |
| 188 | frontier-infra Jebadiah 9B v2.1 (t1e) | 58.0 |
| 189 | decisio 0.4.0 (Qwen3.6-35B-A3B) | 57.7 |
| 190 | GS1 4B | 57.4 |
| 191 | Piccolo 4B | 57.1 |
| 192 | Kahn1 4B (Okura66, Qwen3.5-4B LoRA merge, author's sysone engine) | 56.8 |
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 |