Is JPT-35B-A3B (Qwen3.5-35B-A3B fine-tune) SOTA in Decision models?#128 in Decision modelsRanked #128 in Decision models.
How it scores here
JPT-35B-A3B (Qwen3.5-35B-A3B fine-tune) in Decision models
Primary benchmarks
- Decision Index Full: 54.1 (CI 53.6–54.6) on Nov 21, 2026 (#158 of 420).
- JevBench: 70.7 (CI 70.2–71.2) on Oct 8, 2026 (#30 of 134).
On the category's weighted score it is 29.2 points behind #1 karpo-decision-31B and 0.5 behind the next model up, NInfer Qwen3.8-27B NVFP4.
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 125 | KnowLine 9B Gen2 | 71.6 |
| 126 | StartLux-Decision v1.1 9B | 71.3 |
| 127 | NInfer Qwen3.8-27B NVFP4 | 71.2 |
| 128 | JPT-35B-A3B (Qwen3.5-35B-A3B fine-tune) | 70.8 |
| 129 | JEV-35B | 70.7 |
| 130 | Open-Jev 27B v1.1 (Zefan Cai, LoRA + decision head on Qwen3.8-27B) | 70.5 |
| 131 | JEV-27B | 70.4 |
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 |