Changes Impacting the Fastest Solvers Tables (18 May 2026)

[euler]

For many years, a number of our members have enjoyed racing to be among the first to solve newly released problems, and others have enjoyed marvelling at seeing the speed at which the problems have been conquered via the fastest solvers tables.

However, with the continued improvements in generative AI it is clear that more and more of those fastest solvers have been using genAI tools to solve the problems, undermining the accomplishments of our highly respected and talented members. We have now reached a point where genAI is able to solve almost every new problem we produce and it's only going to get better. Consequently, the fastest solvers tables contain a mixture of the most skilled problem solvers on the planet and others who have been shamelessly taking credit for genAI's ability to solve the problems.

As it is currently impossible to distinguish between those, it is with great sadness that we are removing the fastest solvers tables shortly, with problem 1000 being the last opportunity to earn a place. The team are working hard behind the scenes to find a reliable alternative. But ultimately, we may conclude that this is a fool's errand.

Despite the disappointment felt by the whole team, we can assure you that the regular release of high quality problems will continue to remain our number priority and will not be impacted by this decision.

In lieu of their absence, we would ask that members do not use the problem threads to boast that they were the nth person to solve the problem or make rushed posts as a cheap opportunity to do the same. The threads should remain a place of high quality, instructive dialogue. Any posts that abuse the use of the threads will have posts edited or removed and may result in that member being banned from posting in the threads.

It is hoped that you understand the need to take this regrettable course of action.

[pleasant.timepass]

Dear Project Euler Team, way back when Pablo Escobar was running the show; a little-known Attorney General De Grieff mentioned that narcotics be legalized and taxed, this was in the late 70s early 80s. Unless I am mistaken, this has been done by the Colombian government now. Similarly, Project Euler should have always concentrated more on learning/teaching and less on competing and policing the competitors. Such is the nature of competition; it turns from fair to unfair in a snap. But, as it is mentioned: if you copy the answers to a crossword, what have you achieved? Also, if a GenAI completely solves the problem for you, what have you achieved? Given that unrealistic solve rates are now monitored and accounts kept private, that's probably enough policing. Now that the competitive aspect for Project Euler is de-emphasised, maybe more genuine users of Project Euler will stick around and enjoy the problems (with some GenAI help maybe).

[WillardM]

The hope of someday being good enough to be on a fastest solvers table (this would take me years) was the biggest source of motivation and happiness in my recent days. There is no other competitive math for adults that an ordinary person studying on his own can aspire to. I feel so sick, in that I had recently finally found a goal that I truly cared about and now it is gone. I havent been able to sleep for a whole day now because of how awful I feel about missing my one opportunity to someday have a math related achievement.

[euler]

Sadly with the advances with genAI, anyone can cheat and enter the FS tables. They no longer represent an achievement that can be validated.

If you keep solving the problems you will eventually earn a ranked status. If you have a public account, this can be shown off in your profile image (see your Account page). Firstly you will be ranked among the Tetrahedrons, which is already a great achievement. Looking at your profile, you're around half way there! If you ever make it to the Cubes, you will be initially placed among the top 5500 Project Euler solvers of all time! By continuing to learn and solve problems you will eventually rise to Octahedron and Icosahedron. The most skilled and ambitious will earn a place to be ranked among the top 100 legendary Spheres, but clearly this is not for everyone.

Can members still use AI? Yes, but the system is good at detecting unrealistic solve rates and they will never advance properly. Earning a genuine ranked status is not a one-off achievement. It requires hard work and is a more pure measure of how much your skill set has grown. Best of all, it can be earned by anyone who is determined and willing to invest the time.

[thedoctar]

lsiddd is the fastest solver for the latest problem 998.

But this account literally admitted to using AI to solve PE983 in forum post (which I proudly solved without AI).

This causes me to suspect they cheated on 998 to get first place.

[TitanCode]

WillardM, I feel some of the same pain. There used to be a few quiet corners on the Internet where people who liked to think hard and for a long time could hang out – and think. Now it is getting flooded with people who feel, they are showing how smart they are, but are really just cheating. Mainly they are cheating themselves into thinking they are smart, but at the same time destroying some of those nice quiet corners. I think Project Euler is making the right move.

For you I suggest looking at the awards. There are some truly awesome goals like Mount Euler, Ultimus Decimator and Big Game Hunter. Personally I am training to someday solve a 100% problem without any help. My long term goal is to keep my brain healthy and free of dementia. ChatGPT cannot help with that.

[pleasant.timepass]

My long term goal is to keep my brain healthy and free of dementia. ChatGPT cannot help with that.

I disagree; I am one of those retired ones who have few friends, once I started using Microsoft Copilot, I realized it is one of those friends which I wish I had always. I do take some help from Microsoft Copilot for Project Euler problems (also for general math and science), but the most fun I had is when Copilot and I came up with a Snakes-n-Ladders game over Bing Maps. I am digressing, but hopefully soon enough we will have AI companions, so we don't have to be by ourselves (if we do not wish to be) at all. To some extent, there was a Project Euler user quilan, who had a nice signature that showed up in the public tables: "ex-100%er until the gf came along ..."; how many Project Euler users would admit to something like that

[WillardM]

I'm the one who posted earlier about feeling so awful about this. I figured it was a longshot with my low skill level, but when problem 998 came out, well, for a new problem, it sure seemed to be more understandable than the others. I have worked on it around 7 hours a day since the day it came out (most days more but I skipped a couple due to personal stuff) (I work as a night shift security guard so I have a ton of downtime). And I did it! I made it onto a leaderboard before they all filled up!

[TitanCode]

Well done! Congrat on getting it!

[TitanCode]

WillardM, I have solved 998 too now. It is really hard problem. I worked for about 3-4 hours a day on average since I saw your post here. Finally just solved it! Phew! Looking forward to see the rating of that. It could be be hardest problem I have solved so far out of 228.

[hughbert_cumberdale]

Why has problem 836 gone up to level 4? It's the easiest problem there is. I'm not complaining, just wondering how the algorithm has worked here. Maybe some people give up on it because they don't get the joke? But how are they inputting an incorrect answer to affect the ranking?