Is Gevva E4B SOTA in Decision models?#334 in Decision modelsRanked #334 in Decision models.
How it scores here
Gevva E4B in Decision models
Primary benchmarks
- Decision Index Full: 29.2 (CI 28.7–29.7) on Nov 21, 2026 (#318 of 420).
On the category's weighted score it is 74.8 points behind #1 karpo-decision-31B and 0.3 behind the next model up, KnowLine 0.8B Gen1.
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 331 | Crivo-1B | 25.8 |
| 332 | lev-350m (Franck Verrot, LFM2.5-350M) | 25.8 |
| 333 | KnowLine 0.8B Gen1 | 25.5 |
| 334 | Gevva E4B | 25.2 |
| 335 | Certo v1 (AltSlate Labs) | 25.0 |
| 336 | StartLux-Decision v1.1 0.8B | 24.9 |
| 337 | EXAONE-4.0-1.2B-JEV v0.3 (unofficial fine-tune of LGAI-EXAONE/EXAONE-4.0-1.2B, native option-label softmax, two reads averaged, self-hosted) | 24.8 |
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 |