GDPval-Rubrics (MiniMax)

MiniMax-M3 74.8% In use

MiniMax rubric grading of model deliverables on public GDPval tasks, in an environment matched to GDPval-AA.

Lab-created in-house eval (MiniMax). The blog spells it 'GPDval-Rubrics'. Built on OpenAI's public GDPval cases.

Made by MiniMax Released Jun 2026 Tasks from real jobs Tasks kept private Last in a launch post Jun 2026 Last model added Jun 2026

Level: Expert Specialists with years of training, often over hours of work
Scored: Graded by a model A language model scores each response, usually against a rubric.
Answers: Open-ended Free-form text, documents, designs or media judged as a whole.

Model scored in lab cards

Launch post lists it, from 1 lab

MiniMax-M3 leads with 74.8%

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

#	Model	Score	Setting	Date	Source
1	MiniMax-M3	74.8%		Jun 2026	Model card

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

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.

MiniMax

Date	Launch post	Score	As the post writes it
1 Jun 2026	MiniMax-M3	74.8	GDPval rubrics