The proof

AVRA only claims a number once it survives the question: how much of that was luck?

Most fantasy tools show you a win rate. AVRA shows you the one that survives: the edge that holds up after stripping out luck, holding back the seasons that cannot be trusted, and refusing to count anything that does not clear the bar. Here is the whole record, including the gate AVRA refused to pass.

Start free today

Early accounts lock founders pricing when paid plans arrive.

The verified backtest

What AVRA's calls did against the consensus rankings.

Verified win-rate edge
Pending validation

AVRA's edge over the consensus is still inside its verification gate. The number shows here only once it survives.

Signal added over the market
Pending validation

AVRA's contribution over the market is still inside its verification gate. The number shows here only once it survives.

Both numbers already have the luck stripped out before they reach this page. A provisional badge means AVRA cannot yet rule out luck, so AVRA does not claim it.

In-season roster decisions

The bigger edge is the moves you make after draft day.

In-season waiver edge
Pending validation

AVRA's waiver edge is still inside its verification gate. The number shows here only once it survives.

Trade evaluation accuracy
Pending validation

AVRA's trade-evaluation edge is still inside its gate. The number shows here only once it survives.

The frozen-before-kickoff wall

Anyone can grade their calls after the games. AVRA freezes its verdict before kickoff.

Every pre-registered call is locked the moment it is made, with a tamper-proof timestamp that cannot be edited once the ball is in the air. The record can never be quietly cleaned up after the fact.

0calls frozen yet

The wall fills as AVRA pre-registers its draft-season verdicts. Every one is locked the moment it is made, so you are watching the record being built in the open, not handed a finished highlight reel.

How AVRA holds itself honest

The number is only as good as what you do to try to break it.

AVRA strips out the luck.

The edge above is smaller than the raw math would give, on purpose: AVRA discounts repeat decisions and the many looks it takes at the data, so a hot streak cannot pass itself off as skill.

AVRA shows what does not clear the bar.

AVRA also ran a Superflex lineup-construction gate. AVRA could not rule out luck on it, so it is marked provisional and not claimed. A tool that only shows you its wins is hiding the rest of the table.

AVRA holds back the seasons it cannot trust.

Earlier seasons whose projections were built with information that only arrived later sit in a separate, flagged block. They never pool into the headline number, because that would quietly inflate it.

Every number passes an automated check.

The win rates, the luck check, and even the sign of the edge are re-verified by continuous integrity gates before anything is allowed to reach this page.

AVRA grades the whole lineup, not just single calls.

Across 51,840 team-weeks in the 2025 backtest, AVRA's lineup calls reached 91.25% of the mathematically optimal lineup, against 88.78% for the public consensus, and that gap added +3.77 percentage points of championship probability across 115,200 simulated seasons.

See what AVRA does for your own league.

AVRA makes the call on every lineup, trade, and waiver, in your scoring, with your roster, against your opponent. AVRA picks a side. The call is always yours to make.

Early accounts lock founders pricing when paid plans arrive.