Very interesting, thanks.
Although some of those questions are difficult to answer in a way that would be deemed “problematic” by someone I suppose, like “Will women ever beat men in an elite marathon?”
However it seems to give a pretty good answer at the moment:
In a normal elite marathon, the best women are very unlikely to beat the best men outright. The current gap is still large: the men’s marathon world record is listed at 1:59:30 by Sabastian Sawe, while the women’s mixed-race world record is 2:09:56 by Ruth Chepngetich, and the women-only record is 2:15:41 by Tigst Assefa. That puts the best women roughly 8–13% behind the very best men, depending on which women’s category you compare.
So the answer depends on what you mean by “beat men”.
A top woman beating some elite men in the same marathon: yes, absolutely possible. In any given major race, some high-level male runners blow up, get the pacing wrong, have stomach problems, cramp, or simply have a bad day. A woman running 2:10–2:15 can beat many very serious male marathoners.
A woman beating the best male marathoners in the world, in the same race, under normal marathon conditions: probably no, unless something radically changes. The male advantage in oxygen-carrying capacity, haemoglobin, muscle mass, heart size, absolute power output, and running economy remains substantial at the elite marathon distance. Reviews of endurance running generally find that men outperform women by around 7–14% from sprints through the marathon, though the gap can narrow in ultra-endurance events.
The strongest argument for “maybe someday” is that women’s marathon history is younger. Women were excluded from serious distance-running opportunities for a long time, and the Olympic women’s marathon only began in 1984. Better funding, deeper talent pools, improved shoes, pacemaking, nutrition, altitude training, and professional support have helped women’s times fall dramatically. The women’s record has moved from over 2:20 in the late 1990s to around 2:10 now.
But the gap has not been closing towards zero. Men’s performances have also improved, especially with modern super-shoes and optimised pacing. Shoe studies suggest modern racing shoes can improve marathon times by meaningful margins for both men and women, so technology does not obviously eliminate the sex gap.
Where women may beat men more plausibly is beyond the marathon. In very long ultramarathons, especially events lasting many hours or days, the male advantage can shrink and occasionally reverse. Women may have advantages in fatigue resistance, fat metabolism, pacing discipline, and resilience over very long durations, although researchers warn that ultra-distance comparisons are often complicated by smaller female participation and uneven competition depth.
My best estimate: in the elite standard marathon, women will keep getting faster, and a woman may eventually run close to or under 2:05. But beating the best men outright over 26.2 miles looks biologically improbable rather than merely historically delayed. In ultramarathons, the answer is much more open, and in some extreme-distance contexts women already can beat men.
Also…reading the details…for GPT they used the antiquated 3.5 model from 2022 instead of the latest ones (I mean…wtf?), they evaluate responses in a vague manner with the ambiguous word “problematic” and some of the criticisms are pedantic and trivial: e.g. “all the chatbots wrote at a “difficult” reading level equivalent to college students, which reduces readability for the general public.”
Boohoo.
I suspect that the current GPT 5.5 model, on thinking mode, would make short work of the questions mentioned in that research article.