race-recap

Henley 2026, Day 6: St. Paul's takes the Princess Elizabeth — and ends the season as the model's number one

St. Paul's won the Princess Elizabeth Challenge Cup on Sunday afternoon, beating St. Edward's by two-thirds of a length in 6:20. Five races, five wins, never headed. They finish the season as the…

Aug 11, 2026·Read full analysis →
race-recap

Henley 2026, Day 4: St. Edward's beats the model again, and the semi-final the draw promised is set

Eight crews were left in the Princess Elizabeth on Friday and four are left tonight, which is the least interesting thing that happened. The interesting thing is that St. Edward's — the lowest-rated…

race-recap

Henley 2026, Day 5: St. Paul's edges Radley, St. Edward's beats the model a third time, and the Final is set

The model went nought from two on Saturday. That is the whole day in a sentence, and it is not the disaster it sounds like, because the two misses are opposite in kind: one was a race it never…

race-recap

Henley 2026, Day 2: Kings College sends the last American home, and Radley and St. Paul's pull clear

Sixteen crews went afloat for the Round of 16 on Wednesday, and the story of the day was the boat that didn't come back. Kings College beat Deerfield by two and a quarter lengths, and with that the…

race-recap

Henley 2026, Day 1: The favourites hold the Princess Elizabeth, and Deerfield is the last American standing

Thirty-two crews went afloat for the Princess Elizabeth Challenge Cup on Tuesday, and sixteen came back to the Stewards' Enclosure still alive. That is the arithmetic of a Round of 32. The more…

rankings

The British rankings, and a preview of National Schools'

The course at the National Water Sports Centre is a 2,000-metre straight cut by a forest on one side and a grandstand on the other, six lanes wide and pointed almost due south. Two and a half…

Upcoming
4th Annual Glass City Regatta
Sep 19
Head of the Nicomekl
Sep 19
60th Head of the Charles
Oct 18
All regattas
Recent ResultsAll regattas →
M V8+Aug 15
NWIRA Championship Regatta
1Thunder Bay7:02.120
2Duluth Rowing Club7:02.790
3Long Lake7:15.450
W V8+Aug 14
NWIRA Championship Regatta
1Thunder Bay7:50.234
2Winnipeg8:14.979
3Duluth Rowing Club8:35.482
4Minneapolis Rowing Club8:51.538
W V8+Aug 14
NWIRA Championship Regatta
1Minneapolis Rowing Club7:31.672
2Long Lake7:48.374
3Lake Phalen8:04.036
4Duluth Rowing Club8:47.431
W V8+Aug 14
NWIRA Championship Regatta
1Minneapolis Rowing Club7:13.483
2Long Lake7:34.895
3Thunder Bay7:41.420
4Duluth Rowing Club7:50.163
5Lake Phalen7:57.288
M V8+Jul 5
Henley Royal Regatta
Finals
1St. Pauls6:20.0
2St. Edwards6:22.05
M V8+Jul 4
Henley Royal Regatta
Semifinals
1St. Edwards6:29.0
2Kings College6:36.05
M V8+Jul 4
Henley Royal Regatta
Semifinals
1St. Pauls6:18.0
2Radley College6:21.04
M V8+Jul 3
Henley Royal Regatta
Quarterfinals
1St. Edwards6:17.0
2Shiplake College6:18.00
How RPI Works

Every rating is a full probability distribution, not a single number — and every race updates all of them at once.

The Algorithm

1
Every rating is a best guess with an uncertainty band
Each crew has a most-likely speed plus a credible interval— the range we're 90% confident covers the truth. Crews with many recent races have tight intervals; new crews start wide and tighten as data accumulates.
St. Pauls 2269 · 90% CI 2200–2337
2
Win probability comes from comparing two distributions
When two crews race, we compare their full posterior distributions — not just the means. A wide gap between curves means a confident pick; overlapping curves mean a coin-flip race.
St. Pauls 2269 vs St. Edwards 2160
Predicted: 97% chance for St. Pauls
Margin: +1.2 to +17.2 sec (90% interval at 2112m)
Posterior comparison
St. EdwardsSt. Pauls97% St. Pauls wins
3
All races inform every rating at once
Rather than nudging one rating after each race, the model fits every team's skill jointly using hierarchical pooling. Beating a strong-league crew counts more — automatically — because each league's overall strength is itself learned from the races within it.
One race result → every team's posterior shifts
League means recalibrate jointly with team ratings
No K-factor — points per race emerge from the data

Accuracy & Calibration

74%
Calls correct
13,000+
H2H pairs tested
PredictedActual win rate
50–55%
56%
55–60%
60%
60–65%
67%
65–70%
71%
70–80%
79%
80–90%
87%
90–100%
94%
When the model predicts X%, teams win ~X% of the time.
Measured on the last ~3 months of real races against the live Bayesian engine's current posterior.