Is Lumma-fev-27B SOTA in Decision models?#102 in Decision modelsRanked #102 in Decision models.
How it scores here
Lumma-fev-27B in Decision models
Primary benchmarks
- Decision Index Full: 60.0 (CI 59.5–60.5) on Nov 21, 2026 (#106 of 420).
On the category's weighted score it is 23.5 points behind #1 karpo-decision-31B and 0.3 behind the next model up, Decision 2.0 Vega 27B (vLLM-SR, Qwen3.8-27B).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 99 | Standard One 35B SH (v1) | 77.1 |
| 100 | NTele-Hybrid-27B-v1 | 76.8 |
| 101 | Decision 2.0 Vega 27B (vLLM-SR, Qwen3.8-27B) | 76.8 |
| 102 | Lumma-fev-27B | 76.5 |
| 103 | Jebadiah 27B (Frontier Infra, Qwen3.8-27B LoRA) | 76.5 |
| 104 | Sieve 27B v2 | 76.2 |
| 105 | mogan-decision-31B-it | 75.9 |
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 |