Is Kev 4B r10 SOTA in Decision models?#291 in Decision modelsRanked #291 in Decision models.
How it scores here
Kev 4B r10 in Decision models
Primary benchmarks
- Decision Index Full: 34.9 (CI 34.4–35.4) on Nov 21, 2026 (#278 of 420).
On the category's weighted score it is 65.2 points behind #1 karpo-decision-31B and 0.1 behind the next model up, OpenSourceJev (Qwen3.5-4B Q4_K_M, native llama.cpp).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 288 | Lev1 3.7B | 35.4 |
| 289 | Jev-Style 2B v4.2 | 35.1 |
| 290 | OpenSourceJev (Qwen3.5-4B Q4_K_M, native llama.cpp) | 34.8 |
| 291 | Kev 4B r10 | 34.8 |
| 292 | Sieve 2B v3 | 34.5 |
| 293 | LatentMesh Blitz 2B v1 | 34.2 |
| 294 | Open-Jev 2B (Zefan Cai) | 34.1 |
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 |