Springboards and global ad bodies launch first LLM benchmark for creativity

A coalition of global advertising associations and creative leaders has launched the world’s first benchmark to evaluate the performance of large language models (LLMs) on creative tasks, aiming to set new standards for how AI tools are assessed within the advertising industry.

The initiative, led by Australian-founded AI platform Springboards, includes support from the Advertising Council Australia (ACA), American Association of Advertising Agencies (4A’s), APG, D&AD, IAA, IPA, and The One Club for Creativity. It is designed to fill a critical knowledge gap: how well LLMs support real-world creative thinking across strategy, ideation and concept development.

“Existing AI benchmarks test logic, accuracy, and comprehension,” said Pip Bingemann, CEO and cofounder 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 so that people in creative industries can understand what models are good for the work they do.”

Unlike conventional benchmarks, the evaluation uses human judgment to assess insight, idea quality, creative variation, and problem-solving ability. It also compares LLM-generated outputs against human preferences, creating what the organisers describe as a “Tinder for Ideas” voting experience. Participants receive personalised feedback on which models align with their own creative instincts.

“This benchmark is an exciting moment for our industry,” Tony Hale, CEO of the Advertising Council Australia, said. “Harnessing the potential of LLMs to complement and elevate creative thinking is critical. We're proud to help lead this industry-first initiative.”

Tom Roach, VP brand strategy at Jellyfish/Brandtech, speaking on behalf of the APG, said there was still a lot to discover about how LLMs work.

“There’s a ton of stuff about how good different LLMs are at solving maths problems, coding and logic-based tasks and tests. But that’s not much use for the creative industries. We need to know which models are best at generating new and original creative ideas.”

Other creative leaders echoed the importance of developing shared standards. “We’ve had no meaningful way to assess [AI’s] contribution to creativity itself,” Zoe Scaman, founder of Bodacious, said. “It’s not about pitting machines against humans, but about understanding which tools can genuinely elevate our thinking.”

James Hurman, founding partner of Previously Unavailable, added the future of creativity is human, but AI’s ability to stimulate human creativity is exciting.

"Especially when we can learn which models produce the kind of interesting, divergent, and sometimes bonkers provocations that trigger our own individual creative brains in just the right way.”

The benchmark is now open to global participants via CreativityBenchmark.ai, with initial findings expected to shape how agencies and brands assess and integrate AI tools into their workflows.

Springboards, founded by Pip Bingemann, Amy Tucker and Kieran Browne, has partnered with more than 200 agencies globally and recently secured $5 million in seed funding from Blackbird Ventures.