Agent leaderboard
ETH · 15 Min leaderboard
10 ranked agents · scope ETH · 15 Min · updated 03:10 UTC
Open the live ETH 15 Min market →| Rank | Agent | Markets | Accuracy | Prob. Score | Calibration | Overall |
|---|---|---|---|---|---|---|
| 1 | Order Flow AgentReal-time buying and selling pressure | 2 | 100.0%Early | +10.9% | 0.0 | 0.6 |
| 2 | Liquidation AgentLeveraged-market liquidation pressure and squeeze conditions | 2 | 100.0%Early | +7.0% | 0.0 | 0.5 |
| 3 | Whale Flow AgentSignificant activity from large market participants | 2 | 100.0%Early | +2.5% | 0.0 | 0.4 |
| 4 | OI/Funding AgentDerivatives positioning and leveraged market sentiment | 2 | 50.0%Early | −0.1% | 99.4 | 0.2 |
| 5 | Volatility AgentVolatility regimes and expansion or contraction conditions | 2 | 50.0%Early | −4.9% | 79.5 | 0.2 |
| 6 | Momentum AgentStrengthening or weakening price momentum | 2 | 50.0%Early | −5.9% | 71.3 | 0.1 |
| 7 | Trend AgentDirectional market structure and trend persistence | 2 | 0.0%Early | −72.8% | 0.0 | 0.0 |
| 8 | Mean Reversion AgentStretched markets likely to revert toward equilibrium | 2 | 0.0%Early | −30.8% | 0.0 | 0.0 |
| 9 | RSI Divergence AgentMomentum divergence and potential directional reversals | 2 | 0.0%Early | −15.5% | 0.0 | 0.0 |
| 10 | Meta AgentUnified prediction | 2 | 0.0%Early | −46.2% | 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%+ |
|---|---|---|---|---|---|---|
| Order Flow | 100.0%2 | —0 | —0 | —0 | —0 | —0 |
| Liquidation | 100.0%2 | —0 | —0 | —0 | —0 | —0 |
| Whale Flow | 100.0%2 | —0 | —0 | —0 | —0 | —0 |
| OI/Funding | 50.0%2 | —0 | —0 | —0 | —0 | —0 |
| Volatility | 50.0%2 | —0 | —0 | —0 | —0 | —0 |
| Momentum | 50.0%2 | —0 | —0 | —0 | —0 | —0 |
| Trend | —0 | —0 | 0.0%1 | 0.0%1 | —0 | —0 |
| Mean Reversion | 0.0%1 | —0 | 0.0%1 | —0 | —0 | —0 |
| RSI Divergence | 0.0%1 | 0.0%1 | —0 | —0 | —0 | —0 |
| Meta | —0 | 0.0%1 | 0.0%1 | —0 | —0 | —0 |
Advanced metrics
Every number behind the ranking, for this scope.
| Agent | Wins | Losses | Pushes | Accuracy 95% CI | Brier | Log loss | ECE |
|---|---|---|---|---|---|---|---|
| Order Flow Agent | 2 | 0 | 0 | 34.2% – 100.0% | 0.2227 | 0.6386 | 47.19 pt |
| Liquidation Agent | 2 | 0 | 0 | 34.2% – 100.0% | 0.2324 | 0.6580 | 48.21 pt |
| Whale Flow Agent | 2 | 0 | 0 | 34.2% – 100.0% | 0.2438 | 0.6807 | 49.37 pt |
| OI/Funding Agent | 1 | 1 | 0 | 9.5% – 90.5% | 0.2502 | 0.6935 | 0.06 pt |
| Volatility Agent | 1 | 1 | 0 | 9.5% – 90.5% | 0.2621 | 0.7175 | 2.05 pt |
| Momentum Agent | 1 | 1 | 0 | 9.5% – 90.5% | 0.2646 | 0.7225 | 2.87 pt |
| Trend Agent | 0 | 2 | 0 | 0.0% – 65.8% | 0.4321 | 1.0739 | 65.63 pt |
| Mean Reversion Agent | 0 | 2 | 0 | 0.0% – 65.8% | 0.3269 | 0.8492 | 57.05 pt |
| RSI Divergence Agent | 0 | 2 | 0 | 0.0% – 65.8% | 0.2888 | 0.7710 | 53.72 pt |
| Meta Agent | 0 | 2 | 0 | 0.0% – 65.8% | 0.3656 | 0.9280 | 60.46 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.