OpenAI launched a brand new benchmark on Thursday that exams how its AI fashions carry out in comparison with human professionals throughout a variety of industries and jobs. The take a look at, GDPval, is an early try at understanding how shut OpenAI’s techniques are to outperforming people at economically invaluable work — a key a part of the corporate’s founding mission to develop synthetic common intelligence, or AGI.
OpenAI says its discovered that its GPT-5 mannequin and Anthropic’s Claude Opus 4.1 “are already approaching the standard of labor produced by business specialists.”
That’s to not say that OpenAI’s fashions are going to begin changing people of their jobs instantly. Regardless of predictions by some CEOs that AI will take the roles of people in only a few years, OpenAI admits that GDPval at this time covers a really restricted variety of duties individuals do of their actual jobs. Nevertheless, it is among the newest methods the corporate is measuring AI’s progress towards this milestone.
GDPval relies on 9 industries that contribute essentially the most to America’s gross home product, together with domains reminiscent of healthcare, finance, manufacturing, and authorities. The benchmark exams an AI mannequin’s efficiency in 44 occupations amongst these industries, starting from software program engineers to nurses to journalists.
For OpenAI’s first model of the take a look at, GDPval-v0, OpenAI requested skilled professionals to match AI-generated experiences with these produced by different professionals, after which select the most effective one. For instance, one immediate requested funding bankers to create a competitor panorama for the last-mile supply business and examine them to AI-generated experiences. OpenAI then averages an AI mannequin’s “win price” towards the human experiences throughout all 44 occupations.
For GPT-5-high, a souped-up model of GPT-5 with additional computational energy, the corporate says the AI mannequin was ranked as higher than or on par with business specialists 40.6% of the time.
OpenAI additionally examined Anthropic’s Claude Opus 4.1 mannequin, which was ranked as higher than or on par with business specialists in 49% of duties. OpenAI says that it believes Claude scored so excessive due to its tendency to make pleasing graphics, moderately than sheer efficiency.
Techcrunch occasion
San Francisco
|
October 27-29, 2025
It’s value noting that almost all working professionals do much more than submit analysis experiences to their boss, which is all that GDPval-v0 exams for. OpenAI acknowledges this and says it plans to create extra strong exams sooner or later that may account for extra industries and interactive workflows.
Nonetheless, the corporate sees the progress on GDPval as notable.
In an interview with Trendster, OpenAI’s chief economist Dr. Aaron Chatterji stated GDPval’s outcomes recommend that individuals in these jobs can now use AI fashions to spend time on extra significant duties.
“[Because] the mannequin is getting good at a few of these issues,” Chatterji says, “individuals in these jobs can now use the mannequin, more and more as capabilities get higher, to dump a few of their work and do doubtlessly larger worth issues.”
OpenAI’s evaluations lead Tejal Patwardhan tells Trendster that she’s inspired by the speed of progress on GDPval. OpenAI’s GPT-4o mannequin scored simply 13.7% (wins and ties versus people), which was launched roughly 15 months in the past. Now GPT-5 scores practically triple that, a pattern Patwardhan expects to proceed.
Silicon Valley has a variety of benchmarks it makes use of to measure the progress of AI fashions and assess whether or not a given mannequin is state-of-the-art. Among the many hottest are AIME 2025 (a take a look at of aggressive math issues) and GPQA Diamond (a take a look at of PhD-level science questions). Nevertheless, a number of AI fashions are nearing saturation on a few of these benchmarks, and lots of AI researchers have cited the necessity for higher exams that may measure AI’s proficiency on real-world duties.
Benchmarks like GDPval might turn out to be more and more essential in that dialog, as OpenAI makes the case that its AI fashions are invaluable for a variety of industries. However OpenAI might have a extra complete model of the take a look at to definitively say its AI fashions can outperform people.
