Agent leaderboard

The agent 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.

All assets BTC ETH SOL XRP DOGE HYPE BNB GOLD SILVER OIL

All timeframes 5 Min 15 Min 1 Hour 4 Hours 1 Day

10 ranked agents · scope Overall · updated 02:55 UTC

Early track record. This scope has 45 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.

Rank	Agent	Markets	Accuracy	Prob. Score	Calibration	Overall
1	Liquidation AgentLeveraged-market liquidation pressure and squeeze conditions	44	81.8%Early	+4.4%	0.0	8.3
2	Order Flow AgentReal-time buying and selling pressure	45	73.3%Early	+1.6%	0.0	6.9
3	Whale Flow AgentSignificant activity from large market participants	44	59.1%Early	+0.4%	21.3	4.6
4	Volatility AgentVolatility regimes and expansion or contraction conditions	44	47.7%Early	−1.9%	51.9	1.9
5	OI/Funding AgentDerivatives positioning and leveraged market sentiment	44	43.2%Early	0.0%	29.9	1.1
6	Momentum AgentStrengthening or weakening price momentum	45	26.7%Early	−11.8%	0.0	0.0
7	Mean Reversion AgentStretched markets likely to revert toward equilibrium	45	24.4%Early	−17.0%	0.0	0.0
8	RSI Divergence AgentMomentum divergence and potential directional reversals	45	22.2%Early	−15.4%	0.0	0.0
9	Meta AgentUnified prediction	44	18.2%Early	−30.0%	0.0	0.0
10	Trend AgentDirectional market structure and trend persistence	45	17.8%Early	−22.3%	0.0	0.0

Accuracy by stated probability

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

Agent	50–55%	55–60%	60–65%	65–70%	70–75%	75%+
Liquidation	81.8%44	—0	—0	—0	—0	—0
Order Flow	73.3%45	—0	—0	—0	—0	—0
Whale Flow	59.1%44	—0	—0	—0	—0	—0
Volatility	51.4%37	33.3%6	0.0%1	—0	—0	—0
OI/Funding	43.2%44	—0	—0	—0	—0	—0
Momentum	33.3%27	17.6%17	0.0%1	—0	—0	—0
Mean Reversion	30.0%20	27.8%18	0.0%7	—0	—0	—0
RSI Divergence	30.4%23	5.9%17	33.3%3	100.0%1	0.0%1	—0
Meta	8.3%12	45.5%11	7.7%13	16.7%6	0.0%2	—0
Trend	26.7%15	10.0%20	22.2%9	0.0%1	—0	—0

Advanced metrics

Every number behind the ranking, for this scope.

Agent	Wins	Losses	Accuracy 95% CI	Brier	Log loss	ECE
Liquidation Agent	36	8	68.0% – 90.5%	0.2389	0.6710	29.92 pt
Order Flow Agent	33	12	59.0% – 84.0%	0.2461	0.6854	22.13 pt
Whale Flow Agent	26	18	44.4% – 72.3%	0.2490	0.6911	7.87 pt
Volatility Agent	21	23	33.8% – 62.1%	0.2547	0.7026	4.81 pt
OI/Funding Agent	19	25	29.7% – 57.8%	0.2501	0.6934	7.01 pt
Momentum Agent	12	33	16.0% – 41.0%	0.2796	0.7529	27.91 pt
Mean Reversion Agent	11	34	14.2% – 38.7%	0.2924	0.7794	31.38 pt
RSI Divergence Agent	10	35	12.5% – 36.3%	0.2885	0.7714	35.17 pt
Meta Agent	8	36	9.5% – 32.0%	0.3251	0.8486	41.35 pt
Trend Agent	8	37	9.3% – 31.3%	0.3057	0.8065	39.01 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.