Is Mica v0.5 4B SOTA in Decision models?#209 in Decision modelsRanked #209 in Decision models.
How it scores here
Mica v0.5 4B in Decision models
Primary benchmarks
- Decision Index Full: 47.7 (CI 47.2–48.2) on Nov 21, 2026 (#201 of 420).
On the category's weighted score it is 46.7 points behind #1 karpo-decision-31B and 0.3 behind the next model up, H2O Lightning E4B v1.0.1.
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 206 | BaseDecision-Dyno (4B) | 53.9 |
| 207 | Decision 4B v1.2 (FlyMyJev, Qwen3.5-4B + LoRA) | 53.8 |
| 208 | H2O Lightning E4B v1.0.1 | 53.6 |
| 209 | Mica v0.5 4B | 53.3 |
| 210 | MetaEncoder v1 | 53.0 |
| 211 | Quyet-1.0-Medium (Chinh Nguyen, Qwen3.5-4B decoder, option-letter logits) | 53.0 |
| 212 | PurpleMIST-Flash-1.0 | 52.8 |
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 |