Applied Compute: Small
Applied Compute · 2026-02-24
Applied Compute: Small is Applied Compute's post-trained GLM-4.7 model, trained with reinforcement learning on 1,885 expert-labeled tasks from Mercor. No public checkpoint or machine identifier is documented, so Atlas tracks it as a benchmark entry.
Benchmark scores
| Benchmark | Score |
|---|---|
| APEX-Agents | 23.0 |