Australian-led benchmarking study puts AI’s creative chops under the spotlight
A new global benchmarking study is set to evaluate large language models (LLMs) for creativity.
The project, led by Australian AI startup Springboards and backed by Advertising Council Australia, D&AD, the IPA, APG, and other industry bodies locally and globally, aims to help agencies and brands identify which AI tools are best fitted for idea generation, lateral thinking and creative variations.
(Springboards.ai)
“Existing AI benchmarks test logic, accuracy, and comprehension,” said Pip Bingemann, CEO and co-founder of Springboards. “But advertising isn’t about right answers—it’s about originality, insight, and impact. This will be the first benchmark designed around the real creative instincts we value in agencies and brands.”
The initiative was developed in collaboration with a global team of AI researchers and creative leaders, and uses a “Tinder for Ideas” platform where participants rate AI-generated ideas for insight, imagination, and creative variation. The objective is to reveal which models most closely align with human creative judgement, and identify variations by geographic region and across industry roles .
Tony Hale, CEO of Advertising Council Australia, said in a release: “Harnessing the potential of LLMs to complement and elevate creative thinking is critical. We’re proud to help lead this industry-first initiative, one that’s not just pushing boundaries, but shaping the future of creativity itself.”
The initiative builds on industry engagement from Unmade’s 2023 Humain conference, where an early version of Springboards was first demonstrated. Bingemann returned to speak at Humain 2025, sharing insights into how AI can be best used in commercial creativity.
Those interested in participating in the benchmarking process can explore the CreativityBenchmark.ai platform.
Have your say