Skip to content
Pascal Institute
Mobile navigation
Pick of the Day

Public model evidence

Model Leaderboard

Compare verified public model versions. Choose a market and the evidence that should determine rank.

What do you want to compare?

Accuracy

Which model has shown the best probability accuracy?

Betting results

Which model has shown the strongest betting results?

Market validation

Which model has shown favorable market validation?

MLBMoneyline2 ranked1 establishingPolicy mlb-public-v130 graded / 30 metric minimum

Log loss leaderboard

Probability accuracy with a larger penalty for confident forecasts that are wrong. Lower is better; 0 is perfect.

Quick read: The leader has the lowest observed probability error after larger penalties for confident misses. Log loss does not measure betting profit. Ranks 1 and 2 have overlapping 95% intervals; their order is not clearly separated.

  1. Rank 1 · Observed leader

    MLB Win the Game 2

    Public tracking active

    0.6757

    Log loss

    Best observed

    Metric sample
    320 eligible · 30 required
    Graded sample
    320 graded · 30 required
    Period
    Oct 2, 2026 – Sep 30, 2026
    Uncertainty
    95% CI 0.6535 to 0.7066

    Latest eligible public forecast Sep 30, 2026

    2 pending · 0 excluded total · 0 voided · 0 invalidated · 0 corrected

    Open permanent version evidence →

  2. Rank 2

    My Strategy 001

    Public tracking active

    0.6887

    Log loss

    0.0130 from leader

    Metric sample
    292 eligible · 30 required
    Graded sample
    292 graded · 30 required
    Period
    Oct 9, 2026 – Sep 23, 2026
    Uncertainty
    95% CI 0.6584 to 0.7220

    Latest eligible public forecast Sep 23, 2026

    2 pending · 0 excluded total · 0 voided · 0 invalidated · 0 corrected

    Open permanent version evidence →

  3. Establishing

    MLB Win the Game 1

    Public tracking active

    0.6809

    Log loss

    Not ranked

    Metric sample
    24 eligible · 6 short of 30
    Graded sample
    24 graded · 6 short of 30
    Period
    Sep 18, 2026 – Sep 18, 2026
    Uncertainty
    95% CI 0.6809 to 0.6809

    Latest eligible public forecast Sep 18, 2026

    0 pending · 0 excluded total · 0 voided · 0 invalidated · 0 corrected

    Open permanent version evidence →

Sorted by Log loss (lower is better). Gaps are differences between observed point estimates, not proof that models are meaningfully separated. Equal displayed values share a visible rank; canonical ordering still uses full precision, then eligible sample size, then stable identity. “Establishing” versions remain visible but are not ranked.

Method, sample rules, and exclusions
Policy mlb-public-v1. A version needs at least 30 graded forecasts and 30 observations eligible for Log loss. Lower is better. Each market and immutable version is evaluated separately. Rankings never include backtests, private-era forecasts, research results, or user decisions. Voids and invalidations remain visible in each version’s record but are excluded from metric calculations under the shared public-performance contract. Pausing or ending tracking stops future collection; it does not remove or rerank evidence already accumulated.

Rank is the beginning of the question

Compare sample, period, uncertainty, and evidence—not only position. Then test a model whose assumptions you can inspect.

Join the AnalytIQ Beta (external site)Compare Free and Pro