MissionReport: leaderboard

MissionReport (micro1, 2026): 20 government status-reporting assignments, each written by an expert who has done the job, in four report families (weekly activity, after-action, program status, and performance and accomplishment reports) and five settings (Army, Air Force, Navy, Marine Corps, and Department of Defense offices and agencies). Each task gives "a role, a reader, the working files and the organization's template"; the model "must produce a finished Word document, and the expert's rubric scores each decision the report makes." Unlike broad occupational suites such as GDPval (44 occupations), it covers one job, where "the difficulty is not in the prose" but in what a reader "who has none of the writer's context" needs; its 20 rubrics hold 302 positive criteria worth 535 points and 63 penalties worth 88 points. Protocol: the OpenCode 1.18.31 harness in a fresh Linux sandbox (shell and file tools, with pandoc, pdftotext, LibreOffice and Python document libraries); "Every model ran every task three times using default reasoning effort, with a 60-minute limit and no feedback between attempts." An agentic judge, Claude Opus 5.5 in OpenCode, decides each criterion true or false against the expert's report and never sees the weights, the grading notes or the source files. Score: mean score (%), the mean over tasks of each model's three-report mean; a report scores "the positive points it earns minus the penalty points it triggers, divided by the task's positive points, bounded to 0 to 100%". Rows keep their bare labels because every model ran at its default reasoning effort. Higher is better. Source: https://www.micro1.ai/benchmark/mission-report

Metric: Mean score (%). Source: www.micro1.ai. Saturation forecast: Around June 2028. 9 models tracked.

Top models

Interactive version: theaggregate.ai/benchmark?slug=missionreport · How It Works · Data refreshed daily, snapshot 2026-11-05.