Quantum X Labs Inc. (Nasdaq: QXL) announced new results from its AI-driven quantum error-correction program, saying its updated decoder demonstrated improved performance against matching-family benchmarks, including Google's published correlated-matching and PyMatching results for the same configuration.

The results were generated using Google's public surface-code dataset from a real quantum-hardware experiment. According to the company, the decoder was trained exclusively on synthetic samples and was not trained on real hardware shots from the Google dataset.

QXL said the outcome supports what it describes as a key principle in its technical roadmap: that error-correction decoders should be able to generalize toward real experimental syndrome data, not only perform well in controlled simulations.

"Our updated decoder improved performance against matching-family benchmarks in this experiment while training only on synthetic data," said Prof. Nir Sharon, Chief Quantum Technology Scientist at Quantum X Labs. "That is a meaningful validation point for our roadmap toward trusted quantum error correction. At the same time, we remain disciplined: this is one benchmark configuration, and our next objective is to replicate and extend the result across additional device centers and code configurations."

The AI component is designed for GPU acceleration and integration with Nvidia CUDA-Q workflows. QXL said its roadmap includes planned syndrome experiments to advance scalable quantum-computing systems.

Quantum X Labs, based in Tel Aviv, operates subsidiaries across quantum technology, digital advertising, and enterprise AI, including Gix Media and Metagramm.