Tensor Machines Launches Open-Source Benchmark to Measure the True Cost of AI Compute

Tensor Machines Launches Open-Source Benchmark to Measure the True Cost of AI Compute

PR Newswire

SAN FRANCISCO, Oct. 7, 2026

New benchmark connects GPU performance and power consumption to the cost of useful AI output

SAN FRANCISCO, Oct. 7, 2026 /PRNewswire/ -- Tensor Machines today announced an open-source AI hardware benchmark designed to help data center operators answer the most pressing economic question: how much useful AI are they getting from the hardware and power they have already bought? The benchmark brings hardware behavior and workload performance into a repeatable assessment of the energy and cost required to produce useful AI output.

GPU specifications and hourly rental prices do not tell an operator how much work a system can sustain. Facility measures such as Power Usage Effectiveness (PUE), describe energy overhead but do not measure the AI output produced by the equipment. Tensor Machines is developing the benchmark around output that meets a workload's service requirements, giving operators a way to evaluate the productive capacity of their infrastructure.

"The economic value of a GPU comes from the useful work it delivers," said Muneeb Rasool, founder and CEO of Tensor Machines. "Operators need to know what that output costs and how the answer changes with the workload, power settings and hardware condition. We are opening up the benchmark so they can measure those tradeoffs and make better use of the infrastructure they already have."

Early findings show why useful output matters

While running their benchmark on several classes of NVIDIA GPUs, Tensor Machines observed differences that a hardware specification or hourly price alone would not reveal:

The same GPU model can deliver different amounts of AI output. On one inference workload, the fastest result delivered nearly 15% more tokens per second than the slowest. At equal hourly GPU prices, that difference would imply nearly 15% higher cost per reported token for the slower result.

More power does not buy proportionately more performance. In a compute comparison, a GPU operating at a higher power cap drew approximately 36% more power while delivering 21% more FP16 compute throughput than its peers.

A performance gap can change with the workload. A group that performed roughly 12% below its peers on one inference workload showed only about a 1% gap on another. A single ranking can miss where hardware is most useful.

The findings are specific to the workloads and operating conditions tested.

A repeatable way to evaluate operating choices

Tensor's benchmark recipe applies different loads and records how hardware draws power, heats up, sustains performance and recovers. The benchmark is designed to connect that physical response to the share of requests meeting service requirements, the energy consumed per accepted output token and the cost of that output. Repeating the same workload after a controlled change would let an operator test whether a different power setting, workload placement or cooling condition improves the result.

Tensor Machines' proprietary physics-based models support this work by analyzing the relationships between power, heat, performance and hardware degradation. The models are in private beta with select bare-metal providers and neo-cloud design partners. The broader goal is to help operators sustain productive output and make informed decisions about hardware use and remaining productive life.

"GPUs have the potential to transform computing at the edge, just as they are transforming data centers, but managing GPU health remains a crucial bottleneck," said Dr. Sandip Roy, professor of electrical and computer engineering at Texas A&M University. "The Texas A&M Global Cyber Research Institute (GCRI) has had the good fortune to collaborate with Tensor Machines, to assess the use of their remarkable GPU health telemetry/analytics for edge applications."

Tensor Machines also announced $1.5 million in pre-seed funding, led by Omni VC. Other investors include Reinforced Ventures, Avesta Fund and Draper U Ventures.

Benchmark launch at the NeoCloud Summit

Rasool will present the open-source benchmark on October 8 at 11 a.m. Pacific at the NeoCloud Summit at Hotel Kabuki in San Francisco, alongside the president of Infrastructure Masons (iMasons). Tensor Machines invites operators, researchers and developers to use the benchmark and contribute to its development.

Benchmark and documentation: https://github.com/tensormachines/TensorBench

About Tensor Machines

Tensor Machines develops physics-based models and benchmarking tools to help AI infrastructure operators understand how power, heat and hardware condition affect useful compute output. Its work focuses on compute yield, energy efficiency and the productive life of GPUs and servers. For more information, visit our website, https://tensormachines.org.

Nicole Conley, Tanis Communications, nicole.conley@taniscomm.com

View original content to download multimedia:https://www.prnewswire.com/news-releases/tensor-machines-launches-open-source-benchmark-to-measure-the-true-cost-of-ai-compute-302900749.html

SOURCE Tensor Machines