Agent leaderboard
BTC · 5 Min leaderboard
10 ranked agents · scope BTC · 5 Min · updated 03:00 UTC
Open the live BTC 5 Min market →| Rank | Agent | Markets | Accuracy | Prob. Score | Calibration | Overall |
|---|---|---|---|---|---|---|
| 1 | Liquidation AgentLeveraged-market liquidation pressure and squeeze conditions | 7 | 85.7%Early | +5.4% | 0.0 | 1.6 |
| 2 | Order Flow AgentReal-time buying and selling pressure | 7 | 71.4%Early | +1.6% | 0.0 | 1.2 |
| 3 | Volatility AgentVolatility regimes and expansion or contraction conditions | 7 | 71.4%Early | +0.2% | 0.0 | 1.1 |
| 4 | Whale Flow AgentSignificant activity from large market participants | 7 | 42.9%Early | −0.4% | 22.7 | 0.2 |
| 5 | RSI Divergence AgentMomentum divergence and potential directional reversals | 7 | 28.6%Early | −13.9% | 0.0 | 0.0 |
| 6 | Trend AgentDirectional market structure and trend persistence | 7 | 14.3%Early | −27.4% | 0.0 | 0.0 |
| 7 | Momentum AgentStrengthening or weakening price momentum | 7 | 14.3%Early | −25.7% | 0.0 | 0.0 |
| 8 | Mean Reversion AgentStretched markets likely to revert toward equilibrium | 7 | 14.3%Early | −27.0% | 0.0 | 0.0 |
| 9 | OI/Funding AgentDerivatives positioning and leveraged market sentiment | 7 | 14.3%Early | −0.6% | 0.0 | 0.0 |
| 10 | Meta AgentUnified prediction | 7 | 14.3%Early | −35.9% | 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 | 85.7%7 | —0 | —0 | —0 | —0 | —0 |
| Order Flow | 71.4%7 | —0 | —0 | —0 | —0 | —0 |
| Volatility | 83.3%6 | 0.0%1 | —0 | —0 | —0 | —0 |
| Whale Flow | 42.9%7 | —0 | —0 | —0 | —0 | —0 |
| RSI Divergence | 50.0%2 | 20.0%5 | —0 | —0 | —0 | —0 |
| Trend | 0.0%1 | 25.0%4 | 0.0%2 | —0 | —0 | —0 |
| Momentum | —0 | 14.3%7 | —0 | —0 | —0 | —0 |
| Mean Reversion | —0 | 16.7%6 | 0.0%1 | —0 | —0 | —0 |
| OI/Funding | 14.3%7 | —0 | —0 | —0 | —0 | —0 |
| Meta | 0.0%1 | 50.0%2 | 0.0%3 | —0 | 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 | 6 | 1 | 0 | 48.7% – 97.4% | 0.2364 | 0.6660 | 33.69 pt |
| Order Flow Agent | 5 | 2 | 0 | 35.9% – 91.8% | 0.2461 | 0.6853 | 19.87 pt |
| Volatility Agent | 5 | 2 | 0 | 35.9% – 91.8% | 0.2494 | 0.6921 | 34.68 pt |
| Whale Flow Agent | 3 | 4 | 0 | 15.8% – 75.0% | 0.2510 | 0.6952 | 7.73 pt |
| RSI Divergence Agent | 2 | 5 | 0 | 8.2% – 64.1% | 0.2849 | 0.7634 | 27.53 pt |
| Trend Agent | 1 | 6 | 0 | 2.6% – 51.3% | 0.3186 | 0.8320 | 43.37 pt |
| Momentum Agent | 1 | 6 | 0 | 2.6% – 51.3% | 0.3142 | 0.8228 | 43.71 pt |
| Mean Reversion Agent | 1 | 6 | 0 | 2.6% – 51.3% | 0.3174 | 0.8297 | 44.26 pt |
| OI/Funding Agent | 1 | 6 | 0 | 2.6% – 51.3% | 0.2516 | 0.6963 | 36.01 pt |
| Meta Agent | 1 | 6 | 0 | 2.6% – 51.3% | 0.3398 | 0.8795 | 46.07 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.