Is MoDe-M SOTA in Decision models?#349 in Decision modelsRanked #349 in Decision models.
How it scores here
MoDe-M in Decision models
Primary benchmarks
- Decision Index Full: 26.5 (CI 26.0–27.0) on Nov 21, 2026 (#332 of 420).
On the category's weighted score it is 77.7 points behind #1 karpo-decision-31B and 0.3 behind the next model up, Saina Helm 2 Omni (0.8B).
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 346 | Ivonnet-0.8B | 22.9 |
| 347 | Qwen3.5-0.8B Decision Model (Mourad Ghafiri) | 22.7 |
| 348 | Saina Helm 2 Omni (0.8B) | 22.6 |
| 349 | MoDe-M | 22.3 |
| 350 | Saif 0.8B Lightning v0.3 | 22.0 |
| 351 | Alibaba GTE Reranker ModernBERT-base | 22.0 |
| 352 | vLLM-SR d3-lite (0.8B) | 21.7 |
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 |