co/efficient
Graded against the actual result across 22 races (from 25 polls, through 2025).
Head-to-head vs VotePredictor Elections
The fair, apples-to-apples test: on the 22 races co/efficient actually polled, how its final poll's margin compared to what VotePredictor Elections predicted for those same races.
| Model | Avg miss (pts) | Called right |
|---|---|---|
| co/efficient | 5.77 | 64% |
| VotePredictor Elections | 5.21 | 82% |
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 (22)
Each race co/efficient 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.
| Race | Their call | Result | Miss | Call |
|---|---|---|---|---|
| 2025 NJ Governor | D+1.0 | D+14.4 | 13.4 | ✓ |
| 2025 VA Governor | D+5.0 | D+15.4 | 10.4 | ✓ |
| 2024 OH-13 House | R+1.0 | D+2.2 | 3.2 | ✗ |
| 2022 AZ Governor | R+3.3 | D+0.7 | 4.0 | ✗ |
| 2022 CO Governor | D+12.0 | D+19.3 | 7.3 | ✓ |
| 2022 NH Governor | R+18.0 | R+15.5 | 2.5 | ✓ |
| 2022 NY Governor | R+1.0 | D+7.3 | 8.3 | ✗ |
| 2022 PA Governor | D+10.0 | D+14.8 | 4.8 | ✓ |
| 2022 NH-1 House | D+4.0 | D+8.1 | 4.1 | ✓ |
| 2022 NH-2 House | R+1.0 | D+11.7 | 12.7 | ✗ |
| 2022 AZ Senate | D+1.8 | D+4.9 | 3.1 | ✓ |
| 2022 CO Senate | D+8.0 | D+14.6 | 6.6 | ✓ |
| 2022 GA Senate | R+3.4 | D+1.0 | 4.4 | ✗ |
| 2022 NH Senate | EVEN | D+9.1 | 9.1 | ✗ |
| 2022 PA Senate | R+3.0 | D+4.9 | 7.9 | ✗ |
| 2022 WA Senate | D+3.0 | D+14.5 | 11.5 | ✓ |
| 2021 VA Governor | R+4.0 | R+1.9 | 2.1 | ✓ |
| 2020 PA-8 House | D+5.0 | D+3.6 | 1.4 | ✓ |
| 2020 KS President | R+17.0 | R+14.7 | 2.3 | ✓ |
| 2020 VT President | D+30.0 | D+35.4 | 5.4 | ✓ |
| 2020 KS Senate | R+12.0 | R+11.4 | 0.6 | ✓ |
| 2019 NC-9 House | EVEN | R+2.0 | 2.0 | ✗ |
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 |
|---|---|---|---|---|
| 1–3 wk | 18 | 5.68 | +0.61 | 67% |
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) |
|---|---|---|---|
| 2020 | 6 | 3.3 | D+0.5 |
| 2022 | 14 | 6.2 | R+6.1 |
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.