The Election Forecast
The front page measures where opinion stands if the election were held today. This page is about the actual election, whenever it comes. We don't compress that into one number: we name the ways the country could move — six scenarios — say how much weight we give each, and put the weighting on the record so you can score us later. That record has its first entry: after Labour's leadership change we ran the evaluation we had committed to in advance, and the most likely single scenario changed.
The six scenarios
Every scenario has an observable trigger — a real-world event that fires a dated review of its weight. One trigger has fired: Labour's leadership change, evaluated on 31 July. The scenario we currently weight most likely is tagged; the tag follows the weights.
Labour recovers under a new leader
How much weight we currently give this: 47.6 in 100
A new Labour leader pulls Green, Liberal Democrat and stay-at-home voters back, lifting Labour without touching the right. This is no longer hypothetical: the polling since the leadership change shows exactly the consolidation this scenario predicted, and it is now the single most likely scenario. Even so, its central projection still has Reform as the largest party — what the recovery changes is that Labour roughly doubles its seats and Reform is denied a majority in most runs of this world.
Chance of a Reform majority in this world: 19.1% · hung parliament 78.9%
Trigger: Fires when Labour elects its new leader. Fired 17 July 2026: Andy Burnham was confirmed as Labour leader unopposed. This weight was set on 31 July by the pre-registered first evaluation of the post-transition polling — the Labour rise is real and is funded from Green and Liberal Democrat voters, the specific pattern this scenario predicts.
Reform remains clearly ahead
How much weight we currently give this: 20 in 100
The current four-way split holds to polling day: Reform clearly ahead but short of half the vote, Labour and the Conservatives both weak, no structural shift. This card used to carry the “current picture” tag — and it is still the front page's picture, projected forward — but since Labour's leadership change the polling has been moving away from it, and as of the 31 July evaluation it is no longer the scenario we weight most likely.
Chance of a Reform majority in this world: 39.5% · hung parliament 60.4%
Trigger: No trigger of its own — weight moves only when one of the other scenarios fires.
Reform replaces the Conservatives
How much weight we currently give this: 9.4 in 100
The realignment completes: Reform keeps absorbing the Conservative vote at the pace seen since 2024, and the Conservatives fall to a rump. Britain has done this once before — Labour replaced the Liberals in the 1920s. In this world Reform wins a large majority.
Chance of a Reform majority in this world: 95.5% · hung parliament 4.5%
Trigger: Fires if Reform sustains 1.75× the Conservative share for two months, or the Conservatives fall below 15%.
Reform slips back moderately
How much weight we currently give this: 7.1 in 100
Reform eases from around 27% to the low twenties. On the historical pattern of voters returning to previous homes, most of that goes to the Conservatives — enough to flip the seat order even though Reform still polls a similar share to Labour.
Chance of a Reform majority in this world: 0.4% · hung parliament 97.7%
Trigger: Fires if Reform's polling average stays below 23.5% for a month; how deep the slide goes is settled at the election itself.
One more uncertainty in this world: Where Reform's lost votes go is itself uncertain — if they return to the Conservatives, this world looks like the numbers shown; if newer switchers go back to Labour instead, Labour does better than shown and the Conservatives worse.
The right splits further
How much weight we currently give this: 3.5 in 100
Restore Britain establishes itself as a real second party of the right and stands widely. The right-of-centre vote fragments three ways, and first-past-the-post punishes the whole bloc: Reform and the Conservatives both fall well short of where their combined vote suggests.
Chance of a Reform majority in this world: 4.2% · hung parliament 95.3%
Trigger: Fires if Restore Britain sustains 5% in polls that ask about it, or declares candidates in over 300 seats.
Reform collapses
How much weight we currently give this: 2.4 in 100
A 2019-Brexit-Party-scale collapse to the low teens. Because Reform's vote is spread widely, first-past-the-post is brutal to it at that level: near-total wipeout in seats, with the Conservatives the main beneficiary. Nothing currently visible would cause this — we give it correspondingly little weight.
Chance of a Reform majority in this world: 0% · hung parliament 84.8%
Trigger: Resolved at the election: Reform finishing at or below 17% counts as the collapse world.
Same country, wildly different parliaments
This is the honest headline. Under first-past-the-post, modest differences in vote share produce enormous differences in seats: across our named worlds Reform spans 6 to 388 seats and the Conservatives 8 to 268 — while the Liberal Democrats barely move. Any single seat number you see, here or anywhere, sits somewhere on ranges like these.
Each dot is one named world. 326 seats is a majority; the scale runs to 400.
The weighted view
Weighting the scenarios together gives a single summary — useful, but only honest with its spread attached.
Chance of a Reform majority: 26.2% — but the worlds we can name span 0% to 95.5%
Chance of a hung parliament: 62.4% — across the named worlds, 4.5% to 97.7%
Weighted seat view (range across named worlds): Reform 265 [6–388] · Lab 152 [74–213] · Con 69 [8–268] · Lib Dem 79 [72–91]
These probabilities sum to 90, not 100: we hold back 10 in 100 for shapes of election we haven't named. The 31 July evaluation moved weight between the named scenarios only — this held-back share was deliberately left unchanged.
What changed, and why
Weights move only when a named trigger fires, and every move is dated and kept. When scenarios resolve, we score the probability we had on them at the time — including the misses. Nothing on this page is ever edited in place.
2026-07-31
Scenario descriptions refreshed to reflect the 31 July evaluation, and “Things stay roughly as they are” renamed “Reform remains clearly ahead”. No weights moved.
Copy only: the descriptions of “Things stay roughly as they are” and “Labour recovers under a new leader” were written before the evaluation and still read as if the pre-change picture were the most likely world. The renamed scenario is the same world, definition and trigger — earlier entries' “Stay as-is” refers to it. Definitions and weights are unchanged by this edit — the weights were adopted at the first scheduled evaluation, recorded in the entry below. The “most likely scenario” tag now follows the weights automatically instead of being written by hand.
Weights: Unchanged: Labour recovers 47.6 · Reform ahead 20 · Reform replaces Con 9.4 · Reform slips 7.1 · Right splits 3.5 · Reform collapses 2.4 · held back 10 (of 100)
2026-07-31
First scheduled evaluation after Labour's leadership change: “Labour recovers under a new leader” becomes the most likely single scenario (18 → 47.6).
Andy Burnham was confirmed as Labour leader on 17 July, which fired this scenario's trigger. Under the evaluation rules committed before his confirmation, we scored the eleven fully post-transition polls against the pre-transition baseline: Labour is up about four points, and — the decisive test — that rise is funded almost entirely by voters returning from the Greens and Liberal Democrats, not from the right. That is this scenario's specific signature, so its weight roughly triples and every other scenario shrinks proportionally. The held-back share is unchanged.
Weights: Labour recovers 47.6 · Stay as-is 20 · Reform replaces Con 9.4 · Reform slips 7.1 · Right splits 3.5 · Reform collapses 2.4 · held back 10 (of 100)
2026-07-06
First publication: the six scenarios, their weights, and their triggers.
Initial weights set under the pre-registered scenario framework — committed before any scenario was run through the seat model. One trigger is already armed: Labour's leadership contest is under way, so “Labour recovers under a new leader” gets a dated review when a successor is elected.
Weights: Stay as-is 34 · Labour recovers 18 · Reform replaces Con 16 · Reform slips 12 · Right splits 6 · Reform collapses 4 · held back 10 (of 100)
What kind of numbers these are
The weights are our stated judgment, not a measured probability — the scenario worlds and the trigger record are the checkable part. The seat numbers inside each world come from the same constituency model as the if-held-today picture, run under that world's assumptions. This forecast uses no betting-market information. How it all works: methodology.