Is RSI-Jev v7.0 VL 3B SOTA in Decision models?#198 in Decision modelsRanked #198 in Decision models.
How it scores here
RSI-Jev v7.0 VL 3B in Decision models
Primary benchmarks
- Decision Index Full: 49.7 (CI 49.2–50.2) on Nov 21, 2026 (#190 of 420).
On the category's weighted score it is 44.3 points behind #1 karpo-decision-31B and 0.1 behind the next model up, Clef-Flash (Cloudflare, Qwen3.5-9B post-train with a joint schema head, multimodal, measured on text).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 195 | Valen-Decision 1.5 4B | 56.2 |
| 196 | Jegue 0.2 (9B) | 55.9 |
| 197 | Clef-Flash (Cloudflare, Qwen3.5-9B post-train with a joint schema head, multimodal, measured on text) | 55.7 |
| 198 | RSI-Jev v7.0 VL 3B | 55.7 |
| 199 | JoshuaSP diffusiongemma (open-jev) | 55.4 |
| 200 | Malkuth-4B (newfull5, Kev post-train) | 55.3 |
| 201 | Decision 4B Preview (EpochEcho) | 55.1 |
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 |