Is Dinah-1 SOTA in Decision models?#400 in Decision modelsRanked #400 in Decision models.
How it scores here
Dinah-1 in Decision models
Primary benchmarks
- Decision Index Full: 16.4 (CI 15.9–16.9) on Nov 21, 2026 (#379 of 420).
On the category's weighted score it is 88.7 points behind #1 karpo-decision-31B and 0.1 behind the next model up, Quyet-1.0-Small (Chinh Nguyen, SEA-LION-ModernBERT-300M encoder with fixed heads).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 397 | Bosun v3.1 1.7B | 11.9 |
| 398 | vLLM-SR Decision 2.0 Kai 0.6B | 11.6 |
| 399 | Quyet-1.0-Small (Chinh Nguyen, SEA-LION-ModernBERT-300M encoder with fixed heads) | 11.4 |
| 400 | Dinah-1 | 11.3 |
| 401 | Kev 0.8B r15 | 11.0 |
| 402 | Crivo-Prumo 32M | 10.7 |
| 403 | SimpleJev (Qwen3.5-0.8B, CPU) | 10.6 |
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 |