Pinned Tweet
How fast is AI's research taste improving?
We find that the experimental research taste of frontier models has doubled every ~3 months since December 2025. The best model, Opus 5.5, now exceeds our expert human baseline. Our human experts are experienced researchers, but most ntier lab.
Why measure research taste? In the AI Futures Model, it largely determines how quickly artificial superintelligence is reached once coding is fully automated.
We find that the experimental research taste of frontier models has doubled every ~3 months since December 2025. The best model, Opus 5.5, now exceeds our expert human baseline. Our human experts are experienced researchers, but most ntier lab.
Why measure research taste? In the AI Futures Model, it largely determines how quickly artificial superintelligence is reached once coding is fully automated.
57
206
1,616
300,723
TasteVal's tasks could help labs hill-climb on research taste if released, so we're publishing the results and methodology but keeping the tasks private. Here's our reasoning, and what would change our minds.
pzeroresearch.com/work/publishin…
pzeroresearch.com/work/publishin…
3
2
67
3,955
We're hiring! Check out our available roles here: jobs.ashbyhq.com/pzeroresearch?…
Read more about TasteVal: pzeroresearch.com/work/tasteval
Read more about TasteVal: pzeroresearch.com/work/tasteval
0
1
48
3,472