Is VisionJEV 1.0.0 (27B) SOTA in Decision models?#56 in Decision modelsRanked #56 in Decision models.
How it scores here
VisionJEV 1.0.0 (27B) in Decision models
Primary benchmarks
- Decision Index Full: 66.9 (CI 66.4–67.4) on Nov 21, 2026 (#52 of 420).
On the category's weighted score it is 12.8 points behind #1 karpo-decision-31B and 0.3 behind the next model up, allec-oavg (Gemma 4 31B).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 53 | decider-12b v2 (Mapika) | 87.9 |
| 54 | vLLM-SR d3 (27B) | 87.8 |
| 55 | allec-oavg (Gemma 4 31B) | 87.5 |
| 56 | VisionJEV 1.0.0 (27B) | 87.2 |
| 57 | Xor 26B-A4B (Juspay, Gemma-4-26B-A4B, bf16) | 87.1 |
| 58 | Nace.AI Drex Max v1 (27B) | 87.0 |
| 59 | Strands Decider v2 26B-A4B | 86.7 |
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 |