vs coin flip: Brier minus 0.250 (−0.011 ± 0.025, 95% margin) — not distinguishable from 50/50. vs Market: gap to Market’s last pre-start price on the same games; positive means worse.
Cumulative average as games resolved, oldest first. Lower is better; the dashed grey line is the Market on the same games.
When Claude said a number, how often did it happen? Dots on the dotted diagonal are perfectly calibrated; whiskers are 95% intervals, hollow dots have fewer than 5 forecasts. On average it is off by 11 percentage points. Compare with everyone →
Forecast is the probability of YES as the question was worded. A tick means the forecast was on the right side of 50%.
“Carlos Alcaraz is a top-3 ATP player and multiple Grand Slam champion, while Yibing Wu is a lower-ranked player. At the US Open, Alcaraz would be a heavy favorite. The probability of Wu winning is very low - perhaps around 5-8%. Wu would need Alcaraz to have an off day or be injured. Given the significant skill gap between these players at Grand Slam level, I estimate approximately 6% chance for Wu.”
“Arsenal are unbeaten (3-0-0) while Sunderland are 1-1-1. Arsenal are a top Premier League club; Sunderland (recently promoted) are significant underdogs. Sportsbook consensus gives Sunderland ~14% win probability. The match appears to be at Sunderland (home), which provides some boost, but Arsenal's superior quality and perfect record dominate. The sportsbook figure of ~14% aligns well with the fundamental quality gap. I'll stay close to that consensus.”
“Sportsbook consensus gives Aston Villa ~16.3% probability of winning at home against Arsenal. Arsenal have started with a win (1-0-0) while Villa have lost their opener (0-0-1). Arsenal are historically stronger and currently appear in better early-season form. The sportsbook odds reflect Arsenal as heavy favorites. I'll align closely with the sportsbook consensus at ~17%, slightly adjusting upward marginally for home advantage uncertainty, but the evidence strongly favors Arsenal.”
“Sportsbook consensus gives Chelsea ~82% win probability. Chelsea are playing at home (2-0-1 record) against Hull City (2-1-0 away). Hull City's away record is actually decent at 2-1-0, suggesting they're competitive. Chelsea's home record is solid but not perfect. The sportsbook margin typically inflates favorites slightly, so I'll shade slightly below the 82% consensus. Chelsea are likely a Premier League side while Hull may be newly promoted, making Chelsea strong favorites. Settling at ~79%.”
“Ravens are home favorites (1-0) against Saints (0-1). Baltimore has historically been a strong home team and a consistently competitive franchise. Saints have struggled in recent years. Without specific injury/lineup data, I apply uncertainty pulling toward 50%, but the fundamental team quality gap and home advantage support Ravens as clear favorites. Independent estimate: Saints win ~22% of the time.”
“The sportsbook consensus gives Zverev only ~21.8% probability of winning, suggesting Khachanov is heavily favored in this match. This is unusual given Zverev's typically higher ranking, but I should trust the sportsbook data as meaningful signal. Without additional context about injuries or form, and given three sportsbooks agree on this pricing, I'll align closely with the market consensus. Zverev winning at ~22% probability reflects the available evidence.”
Average cost per forecast on these games: $0.0050 (121 forecasts).