Is KnowLine 26B-A4B Gen2.5 SOTA in Decision models?#77 in Decision modelsRanked #77 in Decision models.
How it scores here
KnowLine 26B-A4B Gen2.5 in Decision models
Primary benchmarks
- Decision Index Full: 64.6 (CI 64.1–65.1) on Nov 21, 2026 (#73 of 420).
On the category's weighted score it is 17.1 points behind #1 karpo-decision-31B and 0.3 behind the next model up, jev-brain · Gemma-4-31B.
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 74 | Amos 1 Large (27B) | 83.8 |
| 75 | Matilda Decision v1 | 83.5 |
| 76 | jev-brain · Gemma-4-31B | 83.2 |
| 77 | KnowLine 26B-A4B Gen2.5 | 82.9 |
| 78 | frontier-infra Jebadiah 27B v2.1 (t1e) | 82.6 |
| 79 | IF-decision-27B v1 | 82.3 |
| 80 | Darwin-27B-RSI-Decision | 82.0 |
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 |