University of New Hampshire
Graded against the actual result across 93 races (from 218 polls, through 2024).
Head-to-head vs VotePredictor Elections
The fair, apples-to-apples test: on the 85 races University of New Hampshire actually polled, how its final poll's margin compared to what VotePredictor Elections predicted for those same races.
| Model | Avg miss (pts) | Called right |
|---|---|---|
| University of New Hampshire | 5.49 | 85% |
| VotePredictor Elections | 4.48 | 91% |
VotePredictor Elections aggregates all the pollsters, so it's expected to beat any single one on margin — that's the value of averaging. The honest comparison among forecasters is on the combined board.
Every race (91)
Each race University of New Hampshire polled, scored on its final poll — the call right before the vote — against the actual Dem−Rep result. Click a race for its full detail.
Accuracy by time to election
Lower is better. Time to election runs right (election week) to left (~2 months out).
By the numbers
| Time to election | Polls | Avg miss | vs field | Called right |
|---|---|---|---|---|
| ≤1 wk | 66 | 5.04 | +0.80 | 88% |
| 1–3 wk | 68 | 6.48 | +1.42 | 81% |
| 3–6 wk | 61 | 7.13 | +1.43 | 80% |
| 6–9 wk | 23 | 6.35 | +0.21 | 78% |
vs field is this pollster's average miss minus all pollsters' at the same lead time — green beats the field, redtrails it. Our historical polls reach ~2 months out; earlier polling isn't in the record.
Track record by cycle — getting better?
| Year | Polls | Avg miss | Lean (house effect) |
|---|---|---|---|
| 2000 | 6 | 5.7 | D+4.2 |
| 2002 | 12 | 7.5 | D+4.2 |
| 2004 | 13 | 4.8 | R+2.9 |
| 2006 | 12 | 8.6 | R+3.4 |
| 2008 | 25 | 5.5 | D+2.9 |
| 2010 | 17 | 5.5 | D+4.0 |
| 2012 | 24 | 5.5 | R+3.4 |
| 2014 | 20 | 6.7 | D+3.7 |
| 2016 | 30 | 9.5 | D+9.3 |
| 2018 | 8 | 3.4 | D+2.1 |
| 2020 | 15 | 5.2 | D+1.8 |
| 2022 | 17 | 5.8 | R+0.8 |
| 2024 | 18 | 4.3 | D+3.5 |
Do we credit a pollster for fixing its bias? Each cycle, the model re-estimates every pollster's lean from all its earlier polls (walk-forward) and subtracts it before using the poll. We tested weighting recent cycles more — it doesn't help: a pollster's lean in one cycle barely predicts the next (correlation 0.28), so the swings above are mostly noise, and averaging over more history beats chasing the latest cycle. The all-time estimate we use came out within ~0.5% of the best option.