Agent leaderboard
ETH · 5 Min leaderboard
10 ranked agents · scope ETH · 5 Min · updated 03:10 UTC
Open the live ETH 5 Min market →| Rank | Agent | Markets | Accuracy | Prob. Score | Calibration | Overall |
|---|---|---|---|---|---|---|
| 1 | Liquidation AgentLeveraged-market liquidation pressure and squeeze conditions | 9 | 77.8%Early | +4.6% | 0.0 | 1.9 |
| 2 | OI/Funding AgentDerivatives positioning and leveraged market sentiment | 9 | 66.7%Early | −0.1% | 0.0 | 1.4 |
| 3 | Volatility AgentVolatility regimes and expansion or contraction conditions | 9 | 55.6%Early | −0.1% | 60.7 | 1.0 |
| 4 | Whale Flow AgentSignificant activity from large market participants | 9 | 44.4%Early | 0.0% | 29.7 | 0.3 |
| 5 | Order Flow AgentReal-time buying and selling pressure | 9 | 44.4%Early | −3.4% | 25.9 | 0.2 |
| 6 | Momentum AgentStrengthening or weakening price momentum | 9 | 44.4%Early | −2.0% | 17.2 | 0.1 |
| 7 | Trend AgentDirectional market structure and trend persistence | 9 | 22.2%Early | −7.1% | 0.0 | 0.0 |
| 8 | Mean Reversion AgentStretched markets likely to revert toward equilibrium | 9 | 22.2%Early | −21.1% | 0.0 | 0.0 |
| 9 | RSI Divergence AgentMomentum divergence and potential directional reversals | 9 | 22.2%Early | −13.6% | 0.0 | 0.0 |
| 10 | Meta AgentUnified prediction | 9 | 22.2%Early | −23.2% | 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%+ |
|---|---|---|---|---|---|---|
| Liquidation | 77.8%9 | —0 | —0 | —0 | —0 | —0 |
| OI/Funding | 66.7%9 | —0 | —0 | —0 | —0 | —0 |
| Volatility | 55.6%9 | —0 | —0 | —0 | —0 | —0 |
| Whale Flow | 44.4%9 | —0 | —0 | —0 | —0 | —0 |
| Order Flow | 44.4%9 | —0 | —0 | —0 | —0 | —0 |
| Momentum | 44.4%9 | —0 | —0 | —0 | —0 | —0 |
| Trend | 28.6%7 | 0.0%2 | —0 | —0 | —0 | —0 |
| Mean Reversion | —0 | 22.2%9 | —0 | —0 | —0 | —0 |
| RSI Divergence | 33.3%6 | 0.0%3 | —0 | —0 | —0 | —0 |
| Meta | 0.0%1 | 40.0%5 | 0.0%3 | —0 | —0 | —0 |
Advanced metrics
Every number behind the ranking, for this scope.
| Agent | Wins | Losses | Pushes | Accuracy 95% CI | Brier | Log loss | ECE |
|---|---|---|---|---|---|---|---|
| Liquidation Agent | 7 | 2 | 0 | 45.3% – 93.7% | 0.2386 | 0.6703 | 25.80 pt |
| OI/Funding Agent | 6 | 3 | 0 | 35.4% – 87.9% | 0.2502 | 0.6936 | 16.57 pt |
| Volatility Agent | 5 | 4 | 0 | 26.7% – 81.1% | 0.2504 | 0.6939 | 3.93 pt |
| Whale Flow Agent | 4 | 5 | 0 | 18.9% – 73.3% | 0.2501 | 0.6933 | 7.03 pt |
| Order Flow Agent | 4 | 5 | 0 | 18.9% – 73.3% | 0.2584 | 0.7100 | 7.41 pt |
| Momentum Agent | 4 | 5 | 0 | 18.9% – 73.3% | 0.2550 | 0.7032 | 8.28 pt |
| Trend Agent | 2 | 7 | 0 | 6.3% – 54.7% | 0.2678 | 0.7290 | 30.32 pt |
| Mean Reversion Agent | 2 | 7 | 0 | 6.3% – 54.7% | 0.3027 | 0.7995 | 35.98 pt |
| RSI Divergence Agent | 2 | 7 | 0 | 6.3% – 54.7% | 0.2840 | 0.7615 | 32.52 pt |
| Meta Agent | 2 | 7 | 0 | 6.3% – 54.7% | 0.3079 | 0.8111 | 36.55 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.