Is Diorite G4 E4B v1.0 SOTA in Decision models?#249 in Decision modelsRanked #249 in Decision models.
How it scores here
Diorite G4 E4B v1.0 in Decision models
Primary benchmarks
- Decision Index Full: 42.3 (CI 41.8–42.8) on Nov 21, 2026 (#240 of 420).
On the category's weighted score it is 55.7 points behind #1 karpo-decision-31B and 0.3 behind the next model up, Starlord 2B v2.0 Preview.
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 246 | Amber Hybrid 4B | 44.9 |
| 247 | APUS-OpenJev-v1-9B (merged bf16 checkpoint-3000 on Qwen3.5-9B, their own native runtime, full depth, self-hosted) | 44.7 |
| 248 | Starlord 2B v2.0 Preview | 44.6 |
| 249 | Diorite G4 E4B v1.0 | 44.3 |
| 250 | JEV-9B | 44.1 |
| 251 | typecastlm (Mikhail Gribov, Qwen3.5-4B computed head) | 43.9 |
| 252 | Bespoke Nimble 9B v2 | 43.8 |
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 |