Is LFM2.5-2.6B-RLCD SOTA in Decision models?#436 in Decision modelsRanked #436 in Decision models.
How it scores here
LFM2.5-2.6B-RLCD in Decision models
Primary benchmarks
- Decision Index Full: 8.2 (CI 7.7–8.7) on Nov 21, 2026 (#408 of 420).
On the category's weighted score it is 96.5 points behind #1 karpo-decision-31B and 0.3 behind the next model up, JevK5 Lite.
Nearby on the board
| # | Model | Category score |
|---|---|---|
| 433 | GLiNER2.5-Decide | 4.3 |
| 434 | Deem 0.8B v1 | 3.8 |
| 435 | JevK5 Lite | 3.8 |
| 436 | LFM2.5-2.6B-RLCD | 3.5 |
| 437 | Qwen-2.5-1B-RLCD | 3.2 |
| 438 | Laya multilingual | 3.0 |
| 439 | Bekko System One v0 17M | 2.9 |
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 |