or so, it has been unimaginable to disclaim that there was a rise within the hype degree in the direction of AI, particularly with the rise of generative AI and agentic AI. As a knowledge scientist working in a consulting agency, I’ve famous a substantial progress within the variety of enquiries concerning how we are able to leverage these new applied sciences to make processes extra environment friendly or automated. And whereas this curiosity would possibly flatter us knowledge scientists, it typically looks like individuals anticipate magic from AI fashions, as if they might resolve each drawback with nothing greater than a immediate. Alternatively, whereas I personally consider generative and agentic AI has modified (and can proceed to alter) how we work and reside, once we conduct business-process modifications, we should think about its limitations and challenges and see the place it proves to be a superb instrument (as we wouldn’t use a fork, for instance, to chop meals).
As I’m a nerd and perceive how LLMs work, I wished to check their efficiency in a logic sport just like the Spanish model of Wordle towards a logic I had in-built a few hours some years in the past (extra particulars on that may be discovered right here). Particularly, I had the next questions:
- Will my algorithm be higher than LLM fashions?
- How will reasoning capabilities in LLM fashions have an effect on their efficiency?
Constructing an LLM-based resolution
To get an answer by the LLM mannequin, I constructed three essential prompts. The primary one was focused to get an preliminary guess:
Let’s suppose I’m enjoying WORDLE, however in Spanish. It’s a sport the place you need to guess a 5-letter phrase, and solely 5 letters, in 6 makes an attempt. Additionally, a letter could be repeated within the remaining phrase.
First, let’s evaluation the foundations of the sport: Day by day the sport chooses a five-letter phrase that gamers attempt to guess inside six makes an attempt. After the participant enters the phrase they suppose it’s, every letter is marked in inexperienced, yellow, or grey: inexperienced means the letter is appropriate and within the appropriate place; yellow means the letter is within the hidden phrase however not within the appropriate place; whereas grey means the letter is just not within the hidden phrase.
However for those who place a letter twice and one exhibits up inexperienced and the opposite yellow, it means the letter seems twice: as soon as within the inexperienced place, and as soon as in one other place that isn’t the yellow one.
Instance: If the hidden phrase is “PIZZA”, and your first try is “PANEL”, the response would seem like this: the “P” could be inexperienced, the “A” yellow, and the “N”, “E”, and “L” grey.
Since for now we don’t know something in regards to the goal phrase, give me a superb beginning phrase—one that you just suppose will present helpful data to assist us work out the ultimate phrase.
Then, a second immediate could be used to indicate all of the phrase guidelines (the immediate right here is just not proven in full because of house, however the full model additionally had instance video games and instance reasonings):
Now, the concept is that we evaluation the sport technique. I’ll be providing you with the sport outcomes. The thought is that, given this consequence, you recommend a brand new 5-letter phrase. Keep in mind additionally that there are solely 6 complete makes an attempt. I’ll provide the consequence within the following format:
LETTER -> COLORFor instance, if the hidden phrase is PIZZA, and the try is PANEL, I’ll give the consequence on this format:
P -> GREEN (it’s the primary letter of the ultimate phrase)
A -> YELLOW (it’s within the phrase, however not within the second place—as an alternative it’s within the final one)
N -> GRAY (it’s not within the phrase)
E -> GRAY (it’s not within the phrase)
L -> GRAY (it’s not within the phrase)Let’s keep in mind the foundations. If a letter is inexperienced, it means it’s within the place the place it was positioned. If it’s yellow, it means the letter is within the phrase, however not in that place. If it’s grey, it means it’s not within the phrase.
For those who place a letter twice and one exhibits inexperienced and the opposite grey, it means the letter solely seems as soon as within the phrase. However for those who place a letter twice and one exhibits inexperienced and the opposite yellow, it means the letter seems twice: as soon as within the inexperienced place, and one other time in a special place (not the yellow one).
All the data I offer you have to be used to construct your suggestion. On the finish of the day, we wish to “flip” all of the letters inexperienced, since meaning we guessed the phrase.
Your remaining reply should solely include the phrase suggestion—not your reasoning.
The ultimate immediate was used to get a brand new suggestion after having the results of our try:
Right here’s the consequence. Keep in mind that the phrase will need to have 5 letters, that you have to use the foundations and all of the data of the sport, and that the aim is to “flip” all of the letters inexperienced, with not more than 6 makes an attempt to guess the phrase. Take your time to suppose by way of your reply—I don’t want a fast response. Don’t give me your reasoning, solely your remaining consequence.
One thing necessary right here is that I by no means tried to information the LLMs or identified errors or errors within the logic. I wished a pure LLM-based consequence and didn’t wish to bias the answer in any form or kind.
Preliminary experiments
The reality is that my preliminary speculation was that whereas I anticipated my algorithm to be higher than the LLMs, I assumed the Generative AI-based resolution was going to do a fairly good job with out a lot assist, however after some days, I seen some “humorous” behaviors, just like the one under (the place the reply was apparent):
The reply was fairly apparent: it solely needed to swap two letters. Nonetheless, ChatGPT answered with the identical guess as earlier than.
After seeing these sorts of errors, I began to ask about this on the finish of video games, and the LLMs mainly acknowledged their errors, however didn’t present a transparent clarification on their reply:
Whereas these are simply two examples, this sort of habits was standard when producing the pure LLM resolution, showcasing some potential limitations within the reasoning of base fashions.
Outcomes Evaluation
With all this data into account, I ran an experiment for 30 days. For 15 days I in contrast my algorithm towards 3 base LLM fashions:
- ChatGPT’s 4o/5 mannequin (After OpenAI launched GPT-5 mannequin, I couldn’t toggle between fashions on the free-tier model of ChatGPT)
- Gemini’s 2.5-Flash mannequin
- Meta’s Llama 4 mannequin
Right here, I in contrast two essential metrics: the share of wins and a factors system metrics (any inexperienced letter within the remaining guess awarded 3 factors, yellow letters awarded 1 level, and grey letters awarded 0 factors):
As could be seen, my algorithm (whereas particular to this use case, it solely took me a day or so to construct) is the one method that wins daily. Analyzing the LLM fashions, Gemini offers the more serious efficiency, whereas ChatGPT and Meta’s Llama present comparable numbers. Nonetheless, as could be seen on the determine on the proper, there may be nice variability within the efficiency of every mannequin and consistency is one thing that isn’t proven by these options for this specific use case.
Nonetheless, these outcomes wouldn’t be full if we didn’t analyze a reasoning LLM mannequin towards my algorithm (and towards a base LLM mannequin). So, for the next 15 days I additionally in contrast the next fashions:
- ChatGPT’s 4o/5 mannequin utilizing reasoning functionality
- Gemini’s 2.5-Flash mannequin (similar mannequin as earlier than)
- Meta’s Llama 4 mannequin (similar mannequin as earlier than)
Some necessary feedback right here: initially, I deliberate to make use of Grok as properly, however after Grok 4 was launched, the reasoning toggle for Grok 3 disappeared, which made comparisons troublesome; then again, I attempted to make use of Gemini’s 2.5-Professional, however in distinction with ChatGPT’s reasoning choice, using this isn’t a toggle, however a special mannequin which solely allowed me to ship 5 prompts per day, which didn’t enable us to finish a full sport. With this in thoughts, we present the outcomes for the next 15 days:
The reasoning functionality behind LLMs offers an enormous enhance to efficiency on this activity, which requires understanding which letter can be utilized in every place, which of them have been evaluated, remembering all outcomes and understanding all combos. Not solely are the common outcomes higher, but in addition efficiency is extra constant, as within the two video games that weren’t gained, just one letter was missed. Despite this enchancment, the precise algorithm I constructed continues to be barely higher by way of efficiency, however as I discussed earlier, this was finished for this particular activity. One thing attention-grabbing is that for these 15 video games, the bottom LLM fashions (Gemini 2.5 Flash and Llama 4) didn’t win as soon as, and the efficiency was worse than the opposite set, which makes me surprise if the wins that had been achieved earlier than had been fortunate or not.
Ultimate Remarks
The intention of this train has been to attempt to check the efficiency of LLMs towards a particularly constructed algorithm for a activity that requires making use of logic guidelines to generate a profitable consequence. Now we have seen that base fashions don’t have good efficiency, however that reasoning capabilities of LLM options present an necessary enhance, producing comparable efficiency to the outcomes of the tailor-made algorithm I had constructed. One necessary factor to take note of is that whereas this enchancment is actual, with real-world functions and manufacturing programs we additionally should think about response time (reasoning LLM fashions take extra time to generate a solution than base fashions or, on this case, the logic I constructed) and price (in keeping with the Azure OpenAI pricing web page, as of the 30th of August of 2025, the worth of 1M enter tokens for the overall function GPT-4o-mini normal function mannequin is round $0.15, whereas for the o4-mini reasoning mannequin, the price of 1M enter tokens is $1.10). Whereas I firmly consider that LLMs and generative AI will proceed to evolve the way in which we work, we are able to’t deal with them as a Swiss knife that solves all the pieces, with out contemplating its limitations and with out evaluating easy-to-build tailor-made options.
