MissionReport
Gemini 4 Argon 64.1% leads since Oct 2026 Not in model cards Models write government status reports in Word from working files and a template, across 20 expert-written Department of Defense style assignments. Expert rubrics score each decision.
Nine models ran each task three times for 540 graded reports. Judgment and synthesis caused most lost points.
Made by micro1 Released Oct 2026 Documents and spreadsheets All tasks public
Last model added Oct 2026
Scores refreshed 2 Nov 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.
9
Models scored on its own leaderboard
Gemini 4 Argon leads with 64.1%
Best score per model from the benchmark's own leaderboard, read on 2 Nov 2026. Where a model ran with several settings or harnesses, we keep its best.
- 1 Gemini 4 Argon 64.1%
- 2 Claude Sonnet 5.5 63.8%
- 3 Claude Opus 5.5 63.5%
- 4 Claude Fable 5.1 63.3%
- 5
Muse Wonder 62.1% - 6 GPT-6 Astra 61.8%
- 7 GPT-6.1 Sol 61%
- 8 Grok 4.7 59.5%
- 9 Gemini 3.8 Flash 54.3%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini 4 Argon | 64.1% | Sep 2026 | Official leaderboard | |
| 2 | Claude Sonnet 5.5 | 63.8% | Sep 2026 | Official leaderboard | |
| 3 | Claude Opus 5.5 | 63.5% | Sep 2026 | Official leaderboard | |
| 4 | Claude Fable 5.1 | 63.3% | Sep 2026 | Official leaderboard | |
| 5 | Muse Wonder | 62.1% | Oct 2026 | Official leaderboard | |
| 6 | GPT-6 Astra | 61.8% | Sep 2026 | Official leaderboard | |
| 7 | GPT-6.1 Sol | 61% | Sep 2026 | Official leaderboard | |
| 8 | Grok 4.7 | 59.5% | Sep 2026 | Official leaderboard | |
| 9 | Gemini 3.8 Flash | 54.3% | Sep 2026 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Google DeepMind
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
On the benchmark’s own leaderboard
Best so far
No lab model card reports it yet
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark.
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).
Qwen3.8-Omni-Flash 75.3% - 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%