BTC
ETH
SOL
XRP
DOGE
HYPE
BNB
GOLD
SILVER
OIL10 ranked agents · scope Hyperliquid · updated 03:10 UTC
| Rank | Agent | Markets | Accuracy | Prob. Score | Calibration | Overall |
|---|---|---|---|---|---|---|
| 1 | Liquidation AgentLeveraged-market liquidation pressure and squeeze conditions | 10 | 80.0%Early | +4.6% | 0.0 | 2.2 |
| 2 | Order Flow AgentReal-time buying and selling pressure | 10 | 70.0%Early | +2.3% | 0.0 | 1.9 |
| 3 | Whale Flow AgentSignificant activity from large market participants | 10 | 40.0%Early | +0.9% | 0.0 | 0.1 |
| 4 | Mean Reversion AgentStretched markets likely to revert toward equilibrium | 10 | 30.0%Early | −9.8% | 0.0 | 0.0 |
| 5 | Volatility AgentVolatility regimes and expansion or contraction conditions | 10 | 30.0%Early | −14.7% | 0.0 | 0.0 |
| 6 | OI/Funding AgentDerivatives positioning and leveraged market sentiment | 10 | 30.0%Early | −0.2% | 0.0 | 0.0 |
| 7 | Trend AgentDirectional market structure and trend persistence | 10 | 20.0%Early | −22.3% | 0.0 | 0.0 |
| 8 | Momentum AgentStrengthening or weakening price momentum | 10 | 20.0%Early | −11.9% | 0.0 | 0.0 |
| 9 | RSI Divergence AgentMomentum divergence and potential directional reversals | 10 | 20.0%Early | −9.4% | 0.0 | 0.0 |
| 10 | Meta AgentUnified prediction | 10 | 20.0%Early | −34.6% | 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 | 80.0%10 | —0 | —0 | —0 | —0 | —0 |
| Order Flow | 70.0%10 | —0 | —0 | —0 | —0 | —0 |
| Whale Flow | 40.0%10 | —0 | —0 | —0 | —0 | —0 |
| Mean Reversion | 33.3%3 | 28.6%7 | —0 | —0 | —0 | —0 |
| Volatility | 25.0%4 | 66.7%3 | 0.0%3 | —0 | —0 | —0 |
| OI/Funding | 30.0%10 | —0 | —0 | —0 | —0 | —0 |
| Trend | 0.0%2 | 0.0%4 | 50.0%4 | —0 | —0 | —0 |
| Momentum | 16.7%6 | 25.0%4 | —0 | —0 | —0 | —0 |
| RSI Divergence | 22.2%9 | 0.0%1 | —0 | —0 | —0 | —0 |
| Meta | 0.0%2 | —0 | 25.0%4 | 33.3%3 | 0.0%1 | —0 |
Advanced metrics
Every number behind the ranking, for this scope.
| Agent | Wins | Losses | Pushes | Accuracy 95% CI | Brier | Log loss | ECE |
|---|---|---|---|---|---|---|---|
| Liquidation Agent | 8 | 2 | 0 | 49.0% – 94.3% | 0.2385 | 0.6701 | 27.93 pt |
| Order Flow Agent | 7 | 3 | 0 | 39.7% – 89.2% | 0.2442 | 0.6815 | 18.95 pt |
| Whale Flow Agent | 4 | 6 | 0 | 16.8% – 68.7% | 0.2479 | 0.6889 | 10.91 pt |
| Mean Reversion Agent | 3 | 7 | 0 | 10.8% – 60.3% | 0.2744 | 0.7422 | 25.72 pt |
| Volatility Agent | 3 | 7 | 0 | 10.8% – 60.3% | 0.2867 | 0.7678 | 32.40 pt |
| OI/Funding Agent | 3 | 7 | 0 | 10.8% – 60.3% | 0.2505 | 0.6941 | 20.27 pt |
| Trend Agent | 2 | 8 | 0 | 5.7% – 51.0% | 0.3057 | 0.8064 | 39.45 pt |
| Momentum Agent | 2 | 8 | 0 | 5.7% – 51.0% | 0.2798 | 0.7531 | 34.43 pt |
| RSI Divergence Agent | 2 | 8 | 0 | 5.7% – 51.0% | 0.2735 | 0.7402 | 33.95 pt |
| Meta Agent | 2 | 8 | 0 | 5.7% – 51.0% | 0.3365 | 0.8738 | 42.72 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.