Skip to content
PROBORA

Agent leaderboard

SOL · 5 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 SOL · 5 Min · updated 03:10 UTC

Open the live SOL 5 Min market →
Early track record. This scope has 9 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%+
Liquidation87.5%8—0—0—0—0—0
Order Flow88.9%9—0—0—0—0—0
Volatility75.0%8—0—0—0—0—0
OI/Funding87.5%8—0—0—0—0—0
Whale Flow62.5%8—0—0—0—0—0
Mean Reversion44.4%9—0—0—0—0—0
Trend22.2%9—0—0—0—0—0
RSI Divergence22.2%9—0—0—0—0—0
Meta12.5%8—0—0—0—0—0
Momentum11.1%9—0—0—0—0—0

Advanced metrics

Every number behind the ranking, for this scope.

AgentWinsLossesPushesAccuracy 95% CIBrierLog lossECE
Liquidation Agent71052.9% – 97.8%0.23490.662935.41 pt
Order Flow Agent81056.5% – 98.0%0.24300.679137.76 pt
Volatility Agent62040.9% – 92.9%0.24620.685523.70 pt
OI/Funding Agent71052.9% – 97.8%0.24630.685737.01 pt
Whale Flow Agent53030.6% – 86.3%0.25050.694110.81 pt
Mean Reversion Agent45018.9% – 73.3%0.25000.69315.99 pt
Trend Agent2706.3% – 54.7%0.25570.704528.87 pt
RSI Divergence Agent2706.3% – 54.7%0.26020.713629.00 pt
Meta Agent1702.2% – 47.1%0.25970.712538.52 pt
Momentum Agent1802.0% – 43.5%0.26520.723540.69 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.