Skip to main content
Phaseo aggregates public information and benchmark results from model providers and evaluation projects. If you rely on Phaseo to look up, compare, or monitor models, a simple acknowledgement helps others discover the platform.

​
Quick version

If Phaseo was helpful, please just link to it somewhere appropriate (methods, footnote, or acknowledgements):
This work uses model metadata and aggregated benchmark results from Phaseo.

​
Suggested citation (optional)

If you prefer a more formal reference, you can use: 
Phaseo. (2025). Phaseo: Aggregated benchmarks and gateway for AI models. https://phaseo.app
BibTeX (optional): 
@misc{phaseo-2025,
    title  = {Phaseo: Aggregated benchmarks and gateway for AI models},
    author = {{Phaseo Team}},
    year   = {2025},
    url    = {https://phaseo.app}
}

​
Benchmark data

Phaseo does not run benchmarks itself. We surface and normalise scores reported by benchmark authors and model providers. When you use benchmark results that you accessed via Phaseo:
  1. Cite the original benchmark and paper as the primary source.
  2. Optionally acknowledge Phaseo as the place you retrieved or compared the scores.
  3. Include:
  • Benchmark name and split (for example MMLU test).
  • Model identifier and provider.
  • URL to the relevant Phaseo page or API.
  • Date accessed.
Example text:
Benchmark scores were retrieved via Phaseo (MMLU test split), accessed 3 March 2025. Model: openai-gpt-4o, provider: OpenAI.

​
Gateway and tooling

When describing integrations, you can mention Phaseo as the gateway layer rather than as a research benchmark source:
“We used the Phaseo Gateway to unify access to OpenAI, Anthropic, and Google models through a single API.”
Link directly to the API reference so readers can explore further.
Last modified on July 9, 2026