student-performance on S Anand

Which LLMs get you better grades?

Fri, 06 Mar 2026 19:26:47 +0800

In my graded assignments students can pick an AI and “Ask AI” any question at the click of a button. It defaults to Google AI Mode, but other models are available. I know who uses which model and their scores in each assignment.

I asked Codex to test the hypothesis whether using a specific model helps students perform better.

The short answer? Yes. Model choice matters a lot. Across 333 students, here’s how much more/less students score compared with ChatGPT:

Perplexity: increases scores by ~11% points (99.8% sure it has an impact).
Claude: +9% (99.5% sure)
Clipboard:, i.e. just copying to the clipboard and pasting in their choice of AI: +9% points (97.5% sure)
Google: -1% (Not sure. Sorry, Sundar.)

If you are still using default ChatGPT, you are leaving nearly a full letter grade on the table compared to Claude or Perplexity users.

I also looked at exam timing. Do specific models perform better under last-minute pressure?

Statistically, no. The model-by-timing interaction isn’t significant (92% sure). A good model won’t save a rushed submission any better than a bad one.

But procrastination does hurt, regardless of which AI they frantically prompt. In the first graded assignment (GA1), there was a negative correlation (-37%, 100% sure) between submission time and final score.

BTW, I correlated with the most-used model. I can’t guarantee they used that specific model on every single attempt.

Of course, correlation isn’t causation. Maybe Claude writes better code. Or perhaps the kind of student who consciously switches from ChatGPT to Perplexity or Claude is just a better, more engaged student.

But a 9-to-10 point bump is a pretty good reason to experiment.

How to create a data-driven exam strategy

Thu, 09 Oct 2025 01:24:19 +0000

Can ChatGPT give teachers data-driven heuristics on student grades?

I uploaded last term’s scores from about 1,700 students in my Tools in Data Science course and asked ChatGPT:

This sheet contains the scores of students … (and explained the columns).

I want to find out what are the best predictors of the total plus bonus… (and explained how scores are calculated).

I am looking for simple statements with 80%+ correctness along the lines of:

“if ga1_f + ga_4f > x then you will not fail; this is true for 90% of the students” or

“your total will effectively be your p1_f score, within plus or minus 5 marks; this is true for ~90% of the students” or

“if you get below 40% in ga3_f then you will likely fail; 80% of the students who did so fail.”

Earlier predictors (GA1, GA2, maybe GA3) are more useful (to students) …

Two kinds of students: Those who want to avoid failing and those who want to score high….

.. give me the best student advice. Phrase it conversationally and include numerical evidence in simple language.

After a 30 minute conversation, ChatGPT delivered concrete, actionable advice:

One-page student playbook

If you’re behind / “don’t fail”:

Immediate target: GA2 > 45 and GA3 > 55. That alone cuts fail risk to ~16%.
If possible, push >85/85 to get fail to ~8%.
Translation: stop skipping; get partial credit; move into the “safe” GA2/GA3 band.

If you’re aiming for an A:

Path A1 (broad coverage): P2 + ET >= 180 > A ~ 35% (n=169).
Path A2 (also broad): P1 + P2 >= 180 > A ~ 45% (n=161).
If early GAs are fine (GA2/GA3 >=70), keep them steady, but your marginal effort should go to P2 and ET.

If you’re aiming for an S:

Path S1 (most reliable): P2 >= 90 + ROE >= 80 > S ~ 77% (n=26).
Path S2 (elite): P2 >= 90 + ET >= 85 + ROE >= 80 > S ~ 91% (n=11).
Simple rule of thumb: P2 + ROE >= 170 or ET + ROE >= 160 > ~70% S with 0% fails in those groups.
Translation: ace ROE. Use P2 and ET as the second and third pillars.

Students: Don’t study harder. Study what moves the marks. (Learning be damned!)

Teachers: Try this with your course data!

Full chat: https://chatgpt.com/share/68e7034a-7340-800c-b259-0bd51715ad11

Birthday matters

Sun, 15 May 2011 20:33:23 +0000

Does it matter which month you’re born in?

Based on the results of the 20 lakh students taking the Class XII exams at Tamil Nadu over the last 3 years (via Reportbee), it appears that the month you were born in can make a difference of as much as 120 marks out of 1,200 – or 10%!

Most students who took the Class XII exams in 2011 were born between March 1991 and June 1992. The average marks of each student (out of 1200) is shown in the graph below.

Students born in June 1991 scored the lowest – around 720/1200. This suddenly shoots up in July, then in August, and the students born in September score as much as 840/1200 on average. From there on, it’s downhill.

This result is consistent across years. In 2009 and 2010, you see a similar pattern.

Why could this be?

Malcolm Gladwell’s book Outliers offers a clue.

Outliers opens, for example, by examining why a hugely disproportionate number of professional hockey and soccer players are born in January, February and March.

The answer turns out to be completely unrelated to numerology or astrology.

It’s simply that in Canada the eligibility cutoff for age-class hockey is January 1. A boy who turns ten on January 2, then, could be playing alongside someone who doesn’t turn ten until the end of the year—and at that age, in preadolescence, a twelve-month gap in age represents an enormous difference in physical maturity.

In Tamil Nadu, students must be 5 years old before entering Class 1. Schools open mid-June. So students born in June 1994 would barely make it in June 1999 – making them the youngest students in the class. July and August students would be missed – but since many schools implement this policy leniently, they sometimes make it in as well. September borns are often consistently the eldest students in a class.

This pattern reflected in the marks. The eldest – the September 1993 borns – score the highest. The next eldest, the October 1993 borns, score a bit less. And so on. (There are older students who take the exam – the ones born before September 1993 – but many of these are failed students from the previous year, introducing a bias in the results.)

Perhaps this initial advantage that the elder students have over their classmates continues through the years? Whatever the reason, it’s clear that if your child is born in September, he or she already has a 100 mark advantage!

Comments

abhijeet 16 May 2011 8:14 am: “Whatever the reason, it’s clear that if your child is born in September, he or she already has a 100 mark advantage!” But at the cost of being older and “losing” 8-9 months!
Shankar V 16 May 2011 10:00 am: Nice…!! Thank God I was born in July! If not on the crest, I at least made it into the upward curve! ;)
S Anand 16 May 2011 10:21 am: @abhijeet: That reminds me of the “Life is a race” dialogue in 3 Idiots :-) Well, not sure how bad being a bit older is. I personally don’t mind, but maybe others do?
Shailesh 16 May 2011 10:33 am: Oh…now I know why I was getting good marks…. :-) I am born in September…and my headmaster changed my birthdate (to Jul month) in school register to not waste my 8-9 months…..
ravi atluri 16 May 2011 10:47 am: They made me study LKG “TWICE”, because I was born in September and didn’t have enough time to be 3! and I have been an anomaly to the september-born-high-performers trend. If the marks are related to the mugging capacity, which if related to age would explain the graphs only for the schooling during. Would like to see, how would these change in college and bachelors :D One more doubt, I have is, many parents have the dob’s of after-aug-born’s to sometime between may to june. If that’s the case, the months on the graph have to be offset ;)
S Anand 16 May 2011 12:35 pm: @Shailesh – if you got into school early, then statistically, you had a DISadvantage. So guess you were MUCH brighter than your classmates! @Ravi – true. No idea how to correct for the real date of birth, though…
k 17 May 2011 2:53 am: this is similar to the paper on Israeli schools where an externally imposed rule created a disproportionate class size, which helps in identifying the effect of class size on performance. date of birth can help in identifying the effect on performance then.
Vasant 17 May 2011 6:14 am: Ha! Now I know why I scored so less in the boards. It’s when I was born! :-) Jokes aside, brilliant analysis.
Sathya 17 May 2011 6:43 am: Good One ! If you still have access to data, would it be possible to plot the same graph against their “numerology numbers” ? ie., 28th born would be 2+8 = 10 => 1+0 = 1. I used to wonder that astrology ( perhaps numerology ) could provide certain insights and that it astro/numero predictions should be verified using statistics. ( Pls note that I do not suggest astro determines a person’s fate. But perhaps it can predict events with some accuracy. How a person reacts to those events are not in the realm of astrology). I would love to do this if I had access to the data. In case you find it worthwhile, it would be interesting to see if numero number matters at all !
Swetha 19 May 2011 9:34 am: M a September born and a gold medalist . (*Grins*)
Sumit Dhar 21 May 2011 3:36 am: And, I know this is extremely difficult, but was wondering if it would be possible to assess the impact of month in which you were born on your professional growth / salary growth. Or even more simply, if marks are correlated with professional success. We Indians tend to believe that good marks == success at work. Would love to know if data validates this belief. If only this kind of data were available… Maybe HR teams in organizations could perform such an assessment. Cheers, D.
Vish 16 Aug 2011 9:59 am: http://news.bbc.co.uk/2/hi/8227268.stm Summer-borns tend to lose out at school because, in England and Wales, 1 September is the cut-off date for school entry, so they can be up to a year younger than their classmates. June baby Frank Lampard Research by the Institute for Fiscal Studies two years ago found only 53% of girls and 47% of boys born in August reached the expected educational level at age seven in state primary schools in England, compared with 80% and 70% of those born in September. Their sporting prowess is affected too. Older children tend to be bigger and more confident, receive more encouragement, and their advantage grows over time. For unto everyone who hath shall be given. Among the 25 most capped England football players, 11 were born between September and November, while only one, Frank Lampard, was born between June and August. In his case, having an England international for a father probably outweighed the disadvantage. So for educational and sporting opportunities, the cruellest and kindest months sit next to each other in the calendar like resentful neighbours.

Visualising student performance

Mon, 13 Dec 2010 11:51:34 +0000

I’ve been helping with visualising student scores for ReportBee, and here’s what we’ve currently come up with.

Each row is a student’s performance across subjects. Let’s walk through each element here.

The first column shows their relative performance across different subjects. Each dot is their rank in a subject. The dots are colour coded based on the subject (and you can see the colours on the image at the top: English is black, Mathematics is dark blue, etc.)

The grey boxes in the middle shows the quartiles. A dot on the left side means that the student is in the bottom quartile. Student 30 is in the bottom quartile in almost every subject. The grey boxes indicate the 2nd and 3rd quartiles. Dots on the right indicate the top quartile.

This view lets teachers quickly explain how a student is performing – either to the headmistress, or parents, or the student. There is a big difference between a consistently good performer, a consistently poor performer, and one that is very good in some subjects, very poor in others. This view lets the teachers identify which type the student falls under.

For example, student 29 is doing very well in a few subjects, OK is some, but is very bad at computer science. This is clearly an intelligent student, so perhaps a different teaching method might help with computer science. Student 30 is doing badly in almost every subject. So the problem is not subject-specific – it is more general (perhaps motivation, home atmosphere, ability, etc.) Student 31 is consistently in the middle, but above average.

The bars in the middle show a more detailed view, using the students’ marks. The zoomed view above shows the English, Mathematics and Social Science marks for the same 3 students (29, 30, 31). The grey boxes have the same meaning. Anyone to the right of those is in the top quarter. Anyone to the left is in the bottom quarter.

Some of bars have a red or a green circle at the end

The green circle indicates that the student has a top score in the subject. The red circle indicates that the student has a bottom score in the subject. This lets teachers quickly narrow down to the best and worst performers in each subject.

The bars on top of the subjects show the histogram of students’ performances. It is a useful view to get a sense of the spread of marks.

For example, English is significantly biased towards the top half than Mathematics or Science. Mathematics has main “trailing” students at the bottom, while English has fewer, and Social Science has many more.

Most of this explanation is intuitive, really. Once explained (and often, even when not explained), they are easy to remember and apply.

So far, this visualisation answers descriptive questions, like:

Where does this student stand with respect to the class?
Is this student a consistent performer, or does his performance vary a lot?
Does this subject have a consistent performance, or does it vary a lot?

We’re now working on drawing insights from this data. For example:

Is there a difference between the performance across sections?
Do students who perform well in science also do well in mathematics?
Can we group students into “types” or clusters based on their performances?

Will share those shortly.

Comments

Sathya 14 Dec 2010 5:36 am: Very nice post as always ! I was wondering if the bars for the individual subject marks are needed. I mean, the first columns provides this information ( implicitly though). Perhaps a Ruler beneath ( from 0 to 200 ) would help identify the individual score. In an online interface, a tooltip on the dots would suffice. A Ruler may help in the printable version. The advantage is that the report would look less cluttered. May be distinction of subjects etc based on shapes (colors cans till be retained) would make it accessible for color blinded persons.
Shankar V 14 Dec 2010 5:21 am: Interesting visual representation of performance. On the same count, is it possible to visually represent a class performance in different subjects and see how a teacher can positively or negatively influence performance? If the class does significantly worse/better in one specific subject, maybe the teacher or the syllabus is to blame.
V 13 Dec 2010 12:47 pm: Interesting. Liked the way Red and Blue dots are shown on the mark line to denote the top/bottom marks. How did you create the leftmost-dots(relative perf across subjects) - I mean, which tool?
S Anand 13 Dec 2010 1:45 pm: The workflow is CSV -> Python -> SVG -> PDF. The CSV file contains scores. I use a simple templating system (like Tornado/Django/Jinja2) to create the visualisation in SVG. Those dots are circles in SVG. This is converted into PDF using wkhtmltopdf (thanks to http://manu-j.com)
V 14 Dec 2010 2:45 pm: Ok. Thanks. a small nit : Readability is affected with the dots on the left - the one which show the percentiles; though this is a nice representation otherwise.
S Anand 14 Dec 2010 5:21 pm: @Shankar – we’re trying to do that by comparing performance across sections. Will post what we come up with next week. @Sathya – excellent point. I now suspect I put it in only to fill the space in a visually appealing way. There are other ways of compactly representing the marks, including the ruler you mentioned. Will check with some teachers for feedback. @V, did you mean because the dots overlapped each other? Or made it less easy to read horizontally? Or something else?
Dan Murray 22 Dec 2010 6:21 pm: Very interesting use of Sparklines. I find myself wanting to build two separate sets of visualizations for this data. I find myself wanting to create an individual student dashboard with overall score and then the separate subject scores with additional details being made available via pop-ups. Nice work though.
Sanketh 23 Dec 2010 10:46 pm: Nice job! The histograms at the top are a nice addition to judge whether the class grading is biased to one side. I agree with @Sathya that the data in the middle is kind of unnecessarily dominant. I am guessing there is some cute way to combine the bars with an additional dimension (hue, tinge) to add the percentile data to the bars themselves and show all subject data together, but I can’t think of anything concrete right now. Keep up the awesome posts!