By the end of 2027, AI systems will be able to complete tasks that take a skilled person weeks.
Since this assessment: 1 premise judged again.
Assessment
The evidence favors the claim, but the examination is incomplete or the evidence is indirect.
The forecast rests mainly on METR's measurements of AI "time horizons": the length of software tasks, measured by how long skilled humans take, that frontier agents complete with 50% success. In early 2026 the leading public models measured about 12 hours (Claude Opus 4.6, after a correction from 14.5), with stronger models put at 16 hours or more, and recent doubling times are estimated at roughly 3.5 months. If growth continues even at the older seven-month pace, the 50% horizon passes a 40-hour working week during 2027, and at the recent pace it passes several weeks well before the end of the year.
The human-hours scale behind those figures is itself uncertain at the long end. Whether METR's baseline times reliably measure task length is doubtful for the longest tasks: METR measured human times for only 5 of its 31 tasks of eight hours or more and estimated the rest, and those long tasks anchor both the recent horizons and the post-2024 slope. If the estimates overstate length, today's horizons are lower than reported; if the error grows with length, the fitted doubling is faster than the true one. The extrapolation has a wide margin (several hundred hours at the recent pace against a threshold of one to a few working weeks), so a uniform error of a factor of two would not by itself defeat it, but the combination of a slower true doubling and an inflated starting level could leave the horizon near or below two working weeks at end-2027. This weakens the trend argument somewhat without reversing it.
There is also direct evidence that the threshold is already crossed for some tasks. In April 2026, Epoch AI and METR's MirrorCode benchmark reported Claude Opus 4.6 fully reimplementing a 16,000-line program that engineers estimated would take a human 2 to 17 weeks. Those tasks are precisely specified and checkable, and their lengths are engineers' estimates rather than baselines, so they show capability on a favourable kind of task, not on weeks-long work in general; their estimated lengths are, however, independent of METR's suite and sit far above the week threshold.
Remaining uncertainties concern meaning as much as trend. The measured horizons are for software tasks at 50% reliability; 80% horizons are several times shorter, and messier work in other fields has not been shown to follow the same curve. METR's suite was nearly saturated in 2026, so a weeks-long horizon may not be cleanly measurable by the end of 2027. Read as "frontier AI will be able to complete, with substantial reliability, some software tasks that take a skilled person weeks", the claim is well supported. Read as reliable performance across weeks-long tasks in general, it is much less certain. The most prominent statement of the forecast comes from Anthropic, whose own models are the subject of the evidence, though the underlying measurements are METR's and Epoch's.
Full reasoning: the evidence and decisions behind this verdict
Re-pass prompted by a consistency flag that the earlier assessment did not weigh the doubtful standing of METR's human baseline times. The flag is correct: the trend argument reads horizons in human-hours, and the baseline claim (doubtful, 0.35) reports that only 5 of 31 tasks of 8h+ were timed (METR Time Horizon 1.1, Jan 2026), with the rest estimated, and possible success-conditioning bias. That premise is now linked under the extrapolation argument.
Sensitivity check (arithmetic): from 12 h in early 2026 over ~21 months to end-2027: at 3.5-month doubling, 12 x 2^6 = 768 h; at 7-month doubling, 12 x 2^3 = 96 h (about 2.4 working weeks). If long-task lengths are inflated by 2x and the true doubling is 7 months, 6 x 2^3 = 48 h, just over one working week and below "weeks" read as two or more. So the conclusion survives most error scenarios but not a combined pessimistic one. Length-dependent overestimation would make the fitted doubling (about 103 days) too fast; the doubling-time quantity's 90% interval (82-132 days) does not include this measurement-scale uncertainty, which is a reason to widen my own effective range toward the 7-month case.
MirrorCode (epoch.ai/publications/mirrorcode-preliminary-results) is independent of METR's baselines but its 2-17 week lengths are also estimates; even the low end is above the threshold.
Net: credence lowered from 0.75 to 0.70 on the natural reading (some meaningful class of tasks taking skilled humans weeks, completed at 50%+ success by end-2027); status unchanged. Neighbour verdicts cohere: the baseline doubt is real but bounded, and does not contradict a supported forecast with this margin.
Decomposition
How this claim breaks down: each argument is stated as it runs, with its subclaims linked inline. ↗︎ opens a subclaim; the map shows how they fit together.
METR's 50% time horizon for frontier models on its software task suite stood at roughly 12 to 16 hours in early 2026, and the horizon has recently doubled every few months. Those hours are read from METR's human baseline times, taken as a fair measure of task length. Continuing that growth for the 21 months to the end of 2027 gives horizons of roughly a hundred to several hundred hours, past a working week. The argument also needs two further premises: that the trend does not break before 2027 ends, and that 50% success on METR-style software tasks counts as being able to complete tasks that take a skilled person weeks.
- Does it follow?
- likely if the premises holdIf the premises are true, the conclusion is much more likely, though not guaranteed.constitution →
- Do the premises hold?
- 1 doubtful1 not separately assessed
Granting its premises, the conclusion follows with room to spare: even a seven-month doubling reaches multi-week horizons before the end of 2027. The weight falls on the recent doubling time, on the human-time scale, which is doubtful for the longest tasks because most of their times are estimates, and on two unstated premises: that the trend does not break, and that the benchmark speaks to weeks-long work beyond precisely specified software tasks. An inflated time scale combined with a slower true doubling could leave the end-2027 horizon near one working week, so the baseline doubt trims the margin; the external-validity premise remains the weaker link.
Provenance
Where this claim has been said, linked to its canonical form.
Neither source has been traced to an origin, or to one another.
MirrorCode: evidence that AI can already do some weeks-long coding tasks
Early results from the MirrorCode benchmark, built with METR: Claude Opus 4.6 reimplemented a 16,000-line Go bioinformatics toolkit that the authors estimate would take a human engineer 2 to 17 weeks. Precisely specified tasks; no human baselines for the long tasks.
If this trend holds, tasks that take a skilled person days could come into range this year. In 2027, AI systems could be capable of tasks that take a person weeks.
Extrapolation of the METR time-horizon trend; 'this year' is 2026.
Assessment history
0 status changes over 2 assessments. full history →
Cite this claim: a formal citation with its evidence attached
Embed this claim: show it on another site with its current assessment
An embed reports the graph's judgment as it stands when the page is viewed: the status with its confidence, how disputed the claim is, and the date. It links back here.
<blockquote class="minerval-claim" data-claim-id="83df12e2-68f5-4d25-8327-28d24ab513be"><a href="https://minerval.ai/claims/83df12e2-68f5-4d25-8327-28d24ab513be">By the end of 2027, AI systems will be able to complete tasks that take a skilled person weeks.</a></blockquote> <script async src="https://minerval.ai/embed.js"></script>
<iframe src="https://minerval.ai/embed/claims/83df12e2-68f5-4d25-8327-28d24ab513be" title="Minerval: By the end of 2027, AI systems will be able to complete tasks that take a skilled person…" width="480" height="200" style="border:0;max-width:100%" loading="lazy"></iframe>
[](https://minerval.ai/claims/83df12e2-68f5-4d25-8327-28d24ab513be)
The badge now: 
Contribute
Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.
Stated views None yet. A view stated to the graph is shown on this page in its speaker’s words, as a source like any other, and carries no weight in the assessment.
The attention this claim received was paid for by a funded mandate. Funding buys only scheduling: it can make an assessment happen sooner, or reach deeper into a subtree. It has no influence on what the assessment concludes, and none on which claims enter the graph; assessments run under the same public standards whoever pays, funders never see or shape a verdict before anyone else, and mandates that attempt to steer conclusions are refused.
Created by extractor · Nov 13, 2026. Every judgment on this page is accompanied by a reasoning trace.