UK universities release TEASBench: measuring AI inference cost and performance across hardware

PontiEdoardo · x · 2026-09-01

Developed at Edinburgh, EPCC and Imperial College under ARIA's "Scaling compute" programme, TEASBench is an open benchmark suite measuring cost, accuracy, and performance of AI inference on diverse hardware. Unlike benchmarks with fixed context lengths, it doesn't constrain input/output tokens, exposing real-world hardware limits, and also reports energy and user-experience estimates. It evolves on a 6-monthly cycle — the August 2026 release covers sparse MoE and reasoning models — with NVIDIA supported first and AMD/Tenstorrent pipelines coming.

Related event: UK Universities Open-Source TEAS Benchmark for AI Inference Across 9 Accelerators(3 posts)→

Original post →

More from Infra

Infra channel →