Compare the GPT increase from their V2 GPT4o model to their reasoning o1 preview model. The jumps from last years GPT 3.5 -> GPT 4 were also quite large. Secondly if you want to take OpenAI’s own research into account that’s in the second image.
if you want to take OpenAI’s own research into account
No thank you.
OlympicArena validation set (text-only)
“Our extensive evaluations reveal that even advanced models like GPT-4o only achieve a 39.97% overall accuracy (28.67% for mathematics and 29.71% for physics)”
- The OlympicArena analysis that you cited.
The jump from GPT-4o -> o1 (preview not full release) was a 20% cumulative knowledge jump. If that’s not an improvement in accuracy I’m not sure what is.
One of the first things they teach you in Experimental Physics is that you can’t derive a curve from just 2 data points.
You can just as easilly fit an exponential growth curve to 2 points like that one 20% above the other, as you can a a sinusoidal curve, a linear one, an inverse square curve (that actually grows to a peak and then eventually goes down again) and any of the many curves were growth has ever diminishing returns and can’t go beyond a certain point (literally “with a limit”)
I think the point that many are making is that LLM growth in precision is the latter kind of curve: growing but ever slower and tending to a limit which is much less than 100%. It might even be like more like the inverse square one (in that it might actually go down) if the output of LLM models ends up poluting the training sets of the models, which is a real risk.
You showing that there was some growth between two versions of GPT (so, 2 data points, a before and an after) doesn’t disprove this hypotesis. I doesn’t prove it either: as I said, 2 data points aren’t enough to derive a curve.
If you do look at the past growth of precision for LLMs, whilst improvement is still happening, the rate of improvement has been going down, which does support the idea that there is a limit to how good they can get.