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
- February 2026
- Kind
- Tasks from real jobs
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Strongest model tested
- Claude Opus 4.6 #37 on the capability index
- Last in a launch post
- February 2026, dropped before it saturated
- Last model added
- February 2026
- Scores refreshed
- November 12th, 2026
Claude Opus 4.6 leads with 73.5% among models released by February 2026
Best score per model from the benchmark's own leaderboard, read on November 12th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in February 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- Claude Fable 5.2
-
Gemini 4 Carbon - GPT-6 Astra
- Claude Opus 5.5
- and 16 more
- 1 Claude Opus 4.6 73.5%
- 2 Claude Opus 4.5 61.1%
- 3
MiniMax-M2.5 59% - 4 GPT-5.2 54.5%
- 5 Gemini 3 Pro 28.1%
- 6 MiniMax-M2.1 24.6%
Source: Official GDPval-MM leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Opus 4.6 | 73.5% | Feb 2026 | Official leaderboard | |
| 2 | Claude Opus 4.5 | 61.1% | Nov 2025 | Official leaderboard | |
| 3 | MiniMax-M2.5 | 59% | Feb 2026 | Official leaderboard | |
| 4 | GPT-5.2 | 54.5% | Dec 2025 | Official leaderboard | |
| 5 | Gemini 3 Pro | 28.1% | Nov 2025 | Official leaderboard | |
| 6 | MiniMax-M2.1 | 24.6% | Dec 2025 | Official leaderboard |
Labs report scores for 1 model in their cards. We plot every source in the charts below.
2 models have held number one on the official leaderboard since its release in February 2026
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official GDPval-MM leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Sources: Official GDPval-MM leaderboard and labs’ model cards
Labs headline it less often now, last in February 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.
| Date | Launch post | Score | As the post writes it |
|---|---|---|---|
| Feb 12, 2026 | MiniMax-M2.5 | 59 | GDPval-MM |
One lab claim next to the leaderboard
Each score a lab reported for its own model, beside the same model's best score on the leaderboard. Gaps mostly come from different harnesses, effort levels and task subsets. 1 of them match, which usually means one side copied the other. Every benchmark.
| Model | Lab says | Board says | Gap |
|---|---|---|---|
| MiniMax-M2.5 | 59% GDPval-MM | 59% Leaderboard | Same |
More in Economic work
- JobBench In use 130 tasks from 35 occupations workers most want delegated. Agent works through messy reference files, graded by fact-anchored binary rubrics. GLM-5.3 61.4%
- GDPval In use Real work tasks from 44 occupations with reference files. Experts blindly compare model deliverables with expert work. Metric is win-or-tie rate.
Seed2.1 Pro 87.9% - GDPval-AA v2.1 In use Agents with shell and web access complete 220 GDPval gold tasks from 44 occupations. Blind pairwise comparisons give Elo ratings. Claude Opus 5.5 1,846
- AA-Briefcase v1.1 In use Version 1.1 of Artificial Analysis's multi-hour office work evaluation, with Elo ratings fitted by Crowd-BT. Claude Opus 5.5 1,822
- CoWorkBench In use Agent completes long-horizon productivity tasks across computer science, finance, law and medicine. Qwen in-house scoring (method unpublished). Claude Fable 5 75.9%
- OfficeQA In use Grounded reasoning over a large corpus of U.S. Treasury Bulletin documents: locate tables and compute precise numeric answers. Claude Opus 4.7 86.3%