Is karpo-decision-31B SOTA in Decision models?Co-SOTA · Decision modelskarpo-decision-31B is co-SOTA in Decision models with low confidence because primary sources disagree beyond the margin of error (with GLiDE 27B, kudhab (Gemma 4 31B), Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)).
How it scores here
karpo-decision-31B in Decision models
Primary benchmarks
- Decision Index Full: 73.9 (CI 73.4–74.4) on Nov 21, 2026 (#1 of 420).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 1 | karpo-decision-31B | 100.0 |
| 1 | Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout) | 100.0 |
| 1 | GLiDE 27B | 99.7 |
| 1 | kudhab (Gemma 4 31B) | 99.4 |
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 |