Khalifa University鈥檚 6G Research Center, in collaboration with GSMA and a global coalition of operators, researchers, and technology partners, is proud to announce the launch of GSMA Open-Telco LLM Benchmarks 2.0: The first comprehensive evaluation suite purpose-built to measure how large language models perform on real-world telecom tasks.
This first-of-its-kind initiative rigorously assesses models on critical operator workflows, including intent-to-configuration, network troubleshooting, standards interpretation, domain Q&A, and telecom math reasoning, bringing objective, transparent metrics to the heart of AI-native network operations.
Built by the industry, for the industry, the benchmark advances trustworthy AI adoption by combining deep domain understanding, structured reasoning, and operational realism across datasets such as TeleYAML, TeleLogs, 3GPP-TSG, TeleQnA, and TeleMath.
Khalifa University鈥檚 6G Research Center co-leads the Network Management & Configuration track, shaping TeleYAML鈥攖he intent-to-configuration benchmark that translates operator intents into standards-aligned YAML for 5G Core functions, subscriber provisioning, and network slicing.
鈥淏enchmarks that reflect real NOC conditions are essential. Open-Telco 2.0 brings much-needed clarity on where models excel and where domain fine-tuning is required to deliver measurable impact in live networks.鈥� From intent-driven management to autonomous RCA, GSMA Open-Telco LLM Benchmarks 2.0 marks a pivotal step toward transparent, reproducible, and deployment-ready AI in telecom. This reinforces the UAE鈥檚 commitment to global leadership in next-generation networks.
Learn more and explore results
