What AI can do at work now: the professional benchmarks, explained
On defined tasks the best AI matches or beats professionals 84.9% of the time (GDPval). Working alone for hours, the best model completes 16.4% of tasks (GDPx).
GDPvalGDPxMETR time horizonAI benchmarks for jobscan AI do my jobAI agents at work
"Can AI do my job?" is the wrong question for most professionals. AI is already doing part of most knowledge jobs, and the part is growing. Three public benchmarks measure how large that part is, and each measures something different. This guide explains them as of Nov 17, 2026, beside the index data to Oct 30, 2026.
Three measures, three scales
| Benchmark | What it tests | Latest public result |
|---|---|---|
| GDPval (OpenAI), our "professional benchmark" | Defined tasks from 44 occupations; experts compare the AI's deliverable with a professional's, blind | 84.9%, GPT-5.5, Apr 23, 2026 (vendor-reported) |
| GDPx v1.0 (SemiAnalysis), our "working on its own" | Multi-hour tasks in 11 fields, done alone inside real software, up to eight hours each | 16.4%, Claude Fable 5.2, reported Nov 9, 2026 |
| Time horizon (METR) | The length of task, in skilled-human time, an agent finishes alone half the time | About 17 hours, Claude Mythos Preview, Apr 2026 |
Source: Jobs Demand Index, data to Oct 30, 2026.
The scales are not interchangeable. GDPval asks whether a finished deliverable is as good as a professional's. GDPx asks whether the AI can get to a finished result with nobody helping. METR asks how long a task can be before the agent fails half the time.
How fast they are moving
GDPval went from 47.6% to 84.9% in seven months. OpenAI makes the benchmark and sells the model, so treat its launch-post figures as vendor-reported. On METR's estimate the task horizon has doubled about every 129 days since 2023. GDPx is new and hard: under strict pass-or-fail grading every model scored zero on finance and legal at launch. Still, about one multi-hour professional task in six now gets done with no human help.
| Occupation | US hiring demand | Sector postings | BLS growth 2025–35 | Median pay | Live roles in our sample |
|---|---|---|---|---|---|
| Software developers | Rising | +23.8% | +10.2% | $135,980 | 4,544 at 478 companies |
| Accountants and auditors | Cooling | −4.4% | +5.0% | $83,680 | 258 at 118 companies |
| Financial and investment analysts | Rising | +12.2% | +7.2% | $102,740 | 272 at 126 companies |
| Lawyers | Steady | +2.8% | +4.7% | $159,670 | 260 at 138 companies |
| Mechanical engineers | Rising | +44.4% | +11.2% | $104,110 | 530 at 97 companies |
| Computer and information systems managers | Rising | +10.5% | +15.8% | $175,140 | 475 at 178 companies |
Source: Jobs Demand Index, data to Oct 30, 2026. Sector postings are measured for the whole Indeed sector an occupation sits in, year on year. Median pay: BLS OEWS 2025. Live roles: public company job boards, Nov 3, 2026 pull.
Every occupation in the table is covered by GDPval tasks, and most are rated Rising in the US. High benchmark scores and steady hiring sit side by side for now.
What the benchmarks leave out
Each test scores a defined task with a checkable result. None scores the work around it: deciding which problem is worth solving, owning the outcome when it goes wrong, and earning the trust of the decision maker who signs off. That is the blind spot of AI, and it is where a professional's leverage is moving.
What to do with this
Look up your occupation in the occupations search and read its hiring demand next to its observed AI use. Every benchmark result we track, with dates and sources, is on the AI Frontier page.
Limits: benchmark tasks are samples, not whole jobs. Results come from public coverage and lab announcements, recorded with the date we saw them.
Check the occupations in this article
Each page shows US hiring demand and the evidence behind it, the Canadian sector postings trend and provincial outlooks shown separately, and a decision panel for your next move. Related: questions people ask, market charts, build your own chart.
- Software developersRising
- Accountants and auditorsCooling
- Financial and investment analystsRising
- LawyersSteady
- Mechanical engineersRising
- Computer and information systems managersRising
Sources
- OpenAI, GDPval paper, Sep 25, 2025, CC BY 4.0 (arxiv.org, 2510.04374)
- OpenAI, Introducing GPT-5.5, Apr 23, 2026 (openai.com)
- SemiAnalysis, GDPx: measuring frontier model capabilities, Nov 2, 2026 (newsletter.semianalysis.com)
- ArtificialWatch, Claude Fable 5.2 tops SemiAnalysis GDPx at 16.4 percent, Nov 10, 2026 (artificialwatch.com)
- METR, Time Horizon 1.1 results file, retrieved Nov 17, 2026 (metr.org)
Cite: Jobs Demand Index, "What AI can do at work now: the professional benchmarks, explained", Nov 17, 2026 (data to Oct 30, 2026). https://jobsdemandindex.com/insights/what-ai-can-do-at-work-professional-benchmarks. How ratings are built. Plain-text version.
Related insights
Data engineering jobs: postings 37% below 2020, outlook still strong
US data and analytics postings grew 3.9% in a year, close to the all-jobs pace, and remain far under their 2022 peak. The long-run outlook points up.
Tech layoffs top 200,000, yet US software postings are up 23.8%
Layoff trackers count more than 200,000 tech workers cut in 2026. US software postings rose 23.8% in a year, while Canadian postings fell 5.3%.
Leading and lagging: why job postings are the last place AI shows up
AI capability and use have multiplied since May 2024 while US job postings moved by single digits. Among occupations with the most AI use, as many are Rising as Cooling or Falling.