GDPval-MM

Agents produce office deliverables for GDPval tasks in a MiniMax agent framework. A judge model compares full trajectories pairwise and reports a win rate.

In-house MiniMax harness on the public GDPval tasks, so scores depend on its judge and comparison models.

Made by MiniMax Released Feb 2026 Tasks from real jobs All tasks public Last in a launch post Feb 2026 , dropped before it saturated Last model added Feb 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-M2.5 leads with 59%

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

59.0 MiniMax-M2.5

1 MiniMax-M2.5 59%

#	Model	Score	Setting	Date	Source
1	MiniMax-M2.5	59%		Feb 2026	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

Labs headline it less often now, last in Feb 2026

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
12 Feb 2026	MiniMax-M2.5	59	GDPval-MM

MiniMax-M2.5 leads with 59%

Scores over time

Labs headline it less often now, last in Feb 2026

More in Economic work