Is munku (Gemma 4 31B) state of the art?Close.Near-SOTA in Decision models, rank #11.
As of Nov 22, 2026, munku (Gemma 4 31B) is near state of the art, rank #11 in Decision models (since Nov 22, 2026; sources Decision Index Full; methodology v1.0). Close in Decision models: rank #11, 2.9 percentile points behind the leader.
Facts and scores
munku (Gemma 4 31B) is an open-weights text model from Unknown; 31B parameters and no public price.
How it scores
- On Decision Index Full it scores 71.3 (CI 70.8–71.8), #14 of 420 (top 4%); 2.6 behind karpo-decision-31B; Fastino GLiDE 1.2 is 0.2 above and Sieve 31B v3 is 0.2 below.
- On Decision Index Brier it scores 28.1%, #49 of 419 (top 12%); 7.7 pts behind lg-decision-4B; vLLM-SR d3-turbo v1.1 (27B) is 0.2 pts above and IF-decision-27B v1 is 0.1 pts below.
- On Decision Index ECE it scores 4.8%, #136 of 420 (top 33%); 3.7 pts behind KnowLine 9B Gen2; level with karpo-decision-31B above and level with RSI-Jev v5.0 VL 3B below.
History
First result on isitsota: Nov 21, 2026. Best overall rank so far: #11 in Decision models, first held Nov 22, 2026.
Reliability
Index bins for munku (Gemma 4 31B). Confidence on the horizontal axis, accuracy on the vertical axis.
Median 324 ms, same GPU.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| Decision Index Full munku (Gemma 4 31B) | 71.3 70.8–71.8 | 2026-11-21 | INDEP. | snap_decision-index_2026-11-21_release-v4|decision-index-0.4.1 |
Where it sits in the succession
Crown intervals for this model are still empty.
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| Decision models | Near-SOTA | #11 | karpo-decision-31B |
Related pages
- Decision models
- Compare with the current leader in Decision models: karpo-decision-31B
- Compare with the current leader in Decision models: Perplexity Decider v1.1 27B (Qwen3.8-27B, noncausal decision readout)
- Compare with the current leader in Decision models: GLiDE 27B
- Compare with the current leader in Decision models: kudhab (Gemma 4 31B)
- munku (Gemma 4 31B) vs Quyet-1.0-Large (Chinh Nguyen, Gemma-4-31B decoder, option-letter logits)
- munku (Gemma 4 31B) vs REAX 1.3
- munku (Gemma 4 31B) vs Logits Sigma-1 Duo
- Decision Index Full
- Lab: Unknown
Is munku (Gemma 4 31B) SOTA?
As of Nov 22, 2026, munku (Gemma 4 31B) is near state of the art, rank #11 in Decision models (since Nov 22, 2026; sources Decision Index Full; methodology v1.0).
What is munku (Gemma 4 31B) best at?
As of Nov 22, 2026, munku (Gemma 4 31B) is near state of the art, rank #11 in Decision models (since Nov 22, 2026; sources Decision Index Full).
How does munku (Gemma 4 31B) rank in Decision models?
Best current rank: #11 in Decision models, as of Nov 22, 2026.