A discrepancy between first- and third-party benchmark outcomes for OpenAI’s o3 AI mannequin is elevating questions concerning the firm’s transparency and mannequin testing practices.
When OpenAI unveiled o3 in December, the corporate claimed the mannequin might reply simply over a fourth of questions on FrontierMath, a difficult set of math issues. That rating blew the competitors away — the next-best mannequin managed to reply solely round 2% of FrontierMath issues accurately.
“Today, all choices on the market have lower than 2% [on FrontierMath],” Mark Chen, chief analysis officer at OpenAI, stated throughout a livestream. “We’re seeing [internally], with o3 in aggressive test-time compute settings, we’re in a position to recover from 25%.”
As it seems, that determine was possible an higher certain, achieved by a model of o3 with extra computing behind it than the mannequin OpenAI publicly launched final week.
Epoch AI, the analysis institute behind FrontierMath, launched outcomes of its impartial benchmark checks of o3 on Friday. Epoch discovered that o3 scored round 10%, effectively beneath OpenAI’s highest claimed rating.
OpenAI has launched o3, their extremely anticipated reasoning mannequin, together with o4-mini, a smaller and cheaper mannequin that succeeds o3-mini.
We evaluated the brand new fashions on our suite of math and science benchmarks. Results in thread! pic.twitter.com/5gbtzkEy1B
— Epoch AI (@EpochAIResearch) April 18, 2025
That doesn’t imply OpenAI lied, per se. The benchmark outcomes the corporate printed in December present a lower-bound rating that matches the rating Epoch noticed. Epoch additionally famous its testing setup possible differs from OpenAI’s, and that it used an up to date launch of FrontierMath for its evaluations.
“The distinction between our outcomes and OpenAI’s is likely to be resulting from OpenAI evaluating with a extra highly effective inner scaffold, utilizing extra test-time [computing], or as a result of these outcomes have been run on a distinct subset of FrontierMath (the 180 issues in frontiermath-2024-11-26 vs the 290 issues in frontiermath-2025-02-28-private),” wrote Epoch.
According to a put up on X from the ARC Prize Foundation, a corporation that examined a pre-release model of o3, the general public o3 mannequin “is a distinct mannequin […] tuned for chat/product use,” corroborating Epoch’s report.
“All launched o3 compute tiers are smaller than the model we [benchmarked],” wrote ARC Prize. Generally talking, larger compute tiers could be anticipated to realize higher benchmark scores.
Granted, the truth that the general public launch of o3 falls in need of OpenAI’s testing guarantees is a little bit of a moot level, because the firm’s o3-mini-high and o4-mini fashions outperform o3 on FrontierMath, and OpenAI plans to debut a extra highly effective o3 variant, o3-pro, within the coming weeks.
It is, nonetheless, one other reminder that AI benchmarks are finest not taken at face worth — significantly when the supply is an organization with providers to promote.
Benchmarking “controversies” have gotten a typical prevalence within the AI business as distributors race to seize headlines and mindshare with new fashions.
In January, Epoch was criticized for ready to reveal funding from OpenAI till after the corporate introduced o3. Many lecturers who contributed to FrontierMath weren’t knowledgeable of OpenAI’s involvement till it was made public.
More lately, Elon Musk’s xAI was accused of publishing deceptive benchmark charts for its newest AI mannequin, Grok 3. Just this month, Meta admitted to touting benchmark scores for a model of a mannequin that differed from the one the corporate made out there to builders.
