Is Tern-35B-A3B SOTA in Decision models?#139 in Decision modelsRanked #139 in Decision models.
How it scores here
Tern-35B-A3B in Decision models
Primary benchmarks
- Decision Index Full: 56.6 (CI 56.1–57.1) on Nov 21, 2026 (#139 of 420).
On the category's weighted score it is 31.3 points behind #1 karpo-decision-31B and 0.2 behind the next model up, SPX-CD Flash (SurdAI, hosted /v1/systemone, Oct-4 checkpoint).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 136 | Starlord 4B Preview | 69.3 |
| 137 | SingVL S1 4B | 69.0 |
| 138 | SPX-CD Flash (SurdAI, hosted /v1/systemone, Oct-4 checkpoint) | 68.9 |
| 139 | Tern-35B-A3B | 68.7 |
| 140 | Surogate Rune 26B-A4B v3 | 68.4 |
| 141 | LitJev (Qwen3.8-27B) | 68.2 |
| 142 | SynACK Decide 26B-A4B v7 | 68.1 |
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 |