Agent leaderboard
Chainlink leaderboard
10 ranked agents · scope Chainlink · updated 05:35 UTC
| Rank | Agent | Markets | Accuracy | Prob. Score | Calibration | Overall |
|---|---|---|---|---|---|---|
| 1 | Momentum AgentStrengthening or weakening price momentum | 6 | 66.7%Early | +10.7% | 0.0 | 1.8 |
| 2 | RSI Divergence AgentMomentum divergence and potential directional reversals | 6 | 66.7%Early | +8.4% | 0.0 | 1.6 |
| 3 | Trend AgentDirectional market structure and trend persistence | 6 | 66.7%Early | +3.0% | 0.0 | 1.2 |
| 4 | Meta AgentUnified prediction | 6 | 66.7%Early | +0.8% | 0.0 | 1.0 |
| 5 | Order Flow AgentReal-time buying and selling pressure | 6 | 66.7%Early | +0.7% | 0.0 | 1.0 |
| 6 | Volatility AgentVolatility regimes and expansion or contraction conditions | 6 | 66.7%Early | −3.8% | 0.0 | 0.9 |
| 7 | Liquidation AgentLeveraged-market liquidation pressure and squeeze conditions | 6 | 50.0%Early | 0.0% | 99.9 | 0.6 |
| 8 | OI/Funding AgentDerivatives positioning and leveraged market sentiment | 6 | 50.0%Early | 0.0% | 98.8 | 0.6 |
| 9 | Mean Reversion AgentStretched markets likely to revert toward equilibrium | 6 | 50.0%Early | −5.4% | 0.0 | 0.0 |
| 10 | Whale Flow AgentSignificant activity from large market participants | 6 | 33.3%Early | −1.4% | 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%+ |
|---|---|---|---|---|---|---|
| Momentum | 100.0%1 | 0.0%1 | 75.0%4 | —0 | —0 | —0 |
| RSI Divergence | 50.0%2 | 50.0%2 | 100.0%2 | —0 | —0 | —0 |
| Trend | 100.0%1 | 60.0%5 | —0 | —0 | —0 | —0 |
| Meta | 100.0%1 | —0 | 100.0%1 | 50.0%4 | —0 | —0 |
| Order Flow | 66.7%6 | —0 | —0 | —0 | —0 | —0 |
| Volatility | 100.0%3 | 0.0%2 | 100.0%1 | —0 | —0 | —0 |
| Liquidation | 50.0%6 | —0 | —0 | —0 | —0 | —0 |
| OI/Funding | 50.0%6 | —0 | —0 | —0 | —0 | —0 |
| Mean Reversion | 100.0%2 | 25.0%4 | —0 | —0 | —0 | —0 |
| Whale Flow | 33.3%6 | —0 | —0 | —0 | —0 | —0 |
Advanced metrics
Every number behind the ranking, for this scope.
| Agent | Wins | Losses | Pushes | Accuracy 95% CI | Brier | Log loss | ECE |
|---|---|---|---|---|---|---|---|
| Momentum Agent | 4 | 2 | 0 | 30.0% – 90.3% | 0.2233 | 0.6380 | 26.08 pt |
| RSI Divergence Agent | 4 | 2 | 0 | 30.0% – 90.3% | 0.2290 | 0.6505 | 16.93 pt |
| Trend Agent | 4 | 2 | 0 | 30.0% – 90.3% | 0.2426 | 0.6784 | 10.71 pt |
| Meta Agent | 4 | 2 | 0 | 30.0% – 90.3% | 0.2481 | 0.6909 | 25.67 pt |
| Order Flow Agent | 4 | 2 | 0 | 30.0% – 90.3% | 0.2482 | 0.6895 | 15.85 pt |
| Volatility Agent | 4 | 2 | 0 | 30.0% – 90.3% | 0.2594 | 0.7126 | 50.43 pt |
| Liquidation Agent | 3 | 3 | 0 | 18.8% – 81.2% | 0.2500 | 0.6931 | 0.01 pt |
| OI/Funding Agent | 3 | 3 | 0 | 18.8% – 81.2% | 0.2500 | 0.6932 | 0.12 pt |
| Mean Reversion Agent | 3 | 3 | 0 | 18.8% – 81.2% | 0.2635 | 0.7204 | 36.94 pt |
| Whale Flow Agent | 2 | 4 | 0 | 9.7% – 70.0% | 0.2534 | 0.7000 | 17.56 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.