Model Pick Record

Every match prediction the model serves, logged before the game and graded after it. Research project — paper predictions, no real money.

How this record works

Whenever the model rates one side at 51% or higher, that side counts as its pick — no odds, no edge filter, no cherry-picking. Picks are logged before the match starts and graded automatically from results; forfeits and walkovers are void. Sub-51% calls are declared coin flips and sit out of the winrate.

This is a research scoreboard for a prediction model — not betting advice, and no money rides on it.

Headline record

The model's pick won 1233 of 1904 (64.8%) since 30 Jun 2026.

65 coin-flip call(s) (under 51% either way) sit out · 126 void (forfeit/walkover) · 328 awaiting a result

Head-to-head with the market, on the 871 graded pick(s) that had a captured market price: model pick won 67.7% vs 69.0% for simply backing the market favorite (1033 pick(s) had no market and sit outside this comparison).

A raw winrate flatters any model that mostly agrees with the market — the favorite-vs-model bar above, scored on the same matches, is the honest comparison.

Calibration — confidence vs reality

Grouping picks by the model's stated confidence: a well-calibrated model's 70–80% bucket should win about 70–80% of the time. That, not the headline winrate, is the number to watch.

confidencepicks wonwin rate avg stated
51-60%66336755.4%55.3%
60-70%58337564.3%64.8%
70-80%41829670.8%74.5%
80%+24019581.2%85.9%

Model eras — the same record, split by version

Each model promotion starts a new era; every graded pick lands as a tick on its era's band.

v6v6-refit · 2 Julv9v10v11v12 · 17 Julv13 · 28 Julv14 · 12 Augv15 · 24 Augwins ↑ / losses ↓
erawhat changedlivegradedW–Lwin rate (95% CI)avg conf
v5-erapre-refit era21 Jun – 23 Jun0
v6v6 baseline23 Jun – 2 Jul1811–7 61.1% CI 38.6–79.7% — n too small64.3%
v6-refitrefit-all baseline2 Jul – 13 Jul13695–41 69.8% CI 61.7–76.9%65.3%
v9post-Phase-A data13 Jul – 15 Jul1815–3 83.3% CI 60.8–94.2% — n too small69.4%
v10lineup-aware h2h15 Jul1611–5 68.8% CI 44.4–85.8% — n too small62.7%
v11Valve rankings16 Jul189–9 50.0% CI 29.0–71.0% — n too small62.9%
v12schedule strength17 Jul – 26 Jul250152–98 60.8% CI 54.6–66.6%65.6%
v13Elo decay-to-rank28 Jul – 11 Aug378250–128 66.1% CI 61.2–70.7%66.5%
v14per-format cal + data refresh12 Aug – 23 Aug322196–126 60.9% CI 55.4–66.0%64.6%
v15as-of RAPM player ratings24 Aug – 14 Sep813527–286 64.8% CI 61.5–68.0%66.1%

Eras face different slates — compare each model's calibration, not raw win rates. No per-era verdict before 100 graded picks.