Open-sourced in May 2026, HRM-Text is a 1B text generation model based on the HRM architecture, strengthened by task completion and latent space reasoning.
Key Traits #
Data-Efficient Training
Trained on ~40B tokens, using up to 1000× less data than the 4–36T tokens used by the models we benchmark against.
Compact Yet Powerful
Built with 1.15B parameters while remaining competitive with models several times its size on reasoning-heavy benchmarks.
Native Edge Reasoning
Runs locally with a 0.6 GiB footprint at int4 quantization, enabling advanced reasoning without cloud dependency.
Application Domains #
Our architecture powers advanced reasoning across complex, high-impact real-world domains.
Benchmarks #
HRM-Text is a proof-of-concept model with no post-training. The numbers below reflect architecture performance alone.
MATH
DROP
ARC-C
MMLU
Despite its compact size, HRM-Text delivers competitive results across reasoning benchmarks, including 56.2% on MATH, 81.9% on ARC-Challenge, 82.2% on DROP, and 60.7% on MMLU.
Benchmark Explanations #
MATH:
A benchmark that tests mathematical reasoning and problem solving, often requiring multi-step logic rather than simple recall.
ARC-C:
The AI2 Reasoning Challenge- Challenge Set, designed to test science reasoning through difficult grade-school science questions that require inference and commonsense understanding.
DROP:
A reading comprehension benchmark that tests a model’s ability to reason over passages, especially with numbers, counting, comparison, and discrete operations.
MMLU
Massive Multitask Language Understanding, a broad benchmark covering many subjects, used to evaluate general knowledge and multi-domain reasoning.