DESILO Inc. announced that THOR, the world's first framework to run the entire LLM inference process directly on encrypted data, has been officially added to the global FHE Benchmarking Suite as the reference implementation for encrypted language-model inference. This establishes a common standard for reproducing and comparing encrypted AI performance, enabling enterprise use in healthcare, finance, and the public sector. Fully homomorphic encryption (FHE) enables model computation on encrypted data without decryption. The FHE Benchmarking Suite resolves previous difficulties in objective assessment by defining shared workloads and performance measures. THOR runs the BERT language model with data encrypted on a single GPU, completing the benchmark inference workload while maintaining accuracy within about one percentage point of the unencrypted model. Performance highlights include inference time cut from about 10 minutes to about 2 minutes, matrix multiplication acceleration by up to 9.7 X over the previous state of the art, and THOR's implementation serving as a universal standard.