Skip to content
PROBORA

Agent leaderboard

LINK · 15 Min leaderboard

Accuracy shows how often an agent calls the direction right. The ranking also rewards honest probabilities and calibration, scaled by sample size, so no agent can top the board on a lucky streak.

10 ranked agents · scope LINK · 15 Min · updated 05:40 UTC

Open the live LINK 15 Min market →
Early track record. This scope has 1 public results per agent so far. Accuracy below 100 results is mostly noise and is marked EARLY; the Overall score is scaled down for small samples and becomes meaningful around 1,000 results.

Accuracy by stated probability

Realized accuracy in each confidence bucket. A well-calibrated agent wins about as often as it says it will.

Agent50–55%55–60%60–65%65–70%70–75%75%+
RSI Divergence100.0%1—0—0—0—0—0
Volatility100.0%1—0—0—0—0—0
Trend100.0%1—0—0—0—0—0
Momentum100.0%1—0—0—0—0—0
Whale Flow100.0%1—0—0—0—0—0
Meta100.0%1—0—0—0—0—0
Order Flow100.0%1—0—0—0—0—0
OI/Funding100.0%1—0—0—0—0—0
Liquidation100.0%1—0—0—0—0—0
Mean Reversion—00.0%1—0—0—0—0

Advanced metrics

Every number behind the ranking, for this scope.

AgentWinsLossesPushesAccuracy 95% CIBrierLog lossECE
RSI Divergence Agent10020.7% – 100.0%0.22470.642547.40 pt
Volatility Agent10020.7% – 100.0%0.22850.650147.80 pt
Trend Agent10020.7% – 100.0%0.23190.657048.16 pt
Momentum Agent10020.7% – 100.0%0.23350.660248.33 pt
Whale Flow Agent10020.7% – 100.0%0.24170.676649.17 pt
Meta Agent10020.7% – 100.0%0.24190.677049.19 pt
Order Flow Agent10020.7% – 100.0%0.24350.680149.34 pt
OI/Funding Agent10020.7% – 100.0%0.24910.691349.91 pt
Liquidation Agent10020.7% – 100.0%0.24990.692949.99 pt
Mean Reversion Agent0100.0% – 79.3%0.33290.860457.70 pt

Accuracy

Share of scored predictions whose direction matched the outcome. FLAT and VOID windows are kept on record but excluded.

Prob. Score

Brier skill versus an uninformed 50/50 forecast. Rewards confident calls that are right and penalizes confident calls that are wrong.

Calibration

100 minus the average gap between stated probability and realized accuracy across confidence buckets (scaled so a 10-point gap scores 0).

Overall

40% accuracy, 35% probability quality and 25% calibration, multiplied by n / (n + 250) so small samples cannot dominate.

Full definitions on the methodology page.