PMPP-Hard

In use

Agents write GPU kernels for 69 tasks that must be correct, and on 48 of them also run within 1.25 times the reference time. The score is the area under the solved-tasks curve over a 10-hour budget, out of 690 task-hours.

Thinking Machines reports an adapted version with task and grading fixes.

Made by: Sinatras, sponsored by Prime Intellect
Released: July 2026
Kind: GPU kernels
Level: Research frontier
Scored: Checked automatically
Answers: Agent task

Last in a launch post: November 2026
Last model added: November 2026

Model scored in lab cards

Launch post lists it, from 1 lab

Inkling 2 Small leads with 494.3

Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.

Bars Table

494.3 Inkling 2 Small

1 Inkling 2 Small 494.3

Source: Labs’ model cards

#	Model	Score	Setting	Date	Source
1	Inkling 2 Small	494.3		Nov 2026	Lab model card

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Reported by the lab in its model card

Source: Labs’ model cards

One lab put it in a launch post in the last six months

Launch posts from every lab that has listed it, one tick per post. Tall colored ticks include it, and short gray ones leave it out.

Thinking Machines

Date	Launch post	Score	As the post writes it
Nov 5, 2026	Inkling 2 Small	494.3	PMPP-Hard AUC, 494.27 task-hours

Inkling 2 Small leads with 494.3

Scores over time

One lab put it in a launch post in the last six months

More in AI research