Prediction accuracy leaderboard
Ranked by walk-forward prediction accuracy (AUC): how well the model calls this investor's next new buy, out of sample. This is not a return ranking. AUC 0.50 is a coin flip; higher is better. Samples are small and every per-investor edge is noisy and not statistically significant. Research, not advice.
Every other smart-money tracker ranks realised returns. This ranks something only a prediction model can: how well the next new buy is called before it files. As of 2026-06-30. 31 followed investors.
| # | Investor | Predict AUC | Beat index | Quarters | Top predicted buy |
|---|---|---|---|---|---|
| 1 | Two Sigma Two Sigma | 0.775 | 53% | 34 | BIGGQ 71% |
| 2 | Bill Nygren Oakmark | 0.737 | 44% | 34 | DSI 98% |
| 3 | Joel Greenblatt Gotham | 0.726 | 32% | 34 | PJX 36% |
| 4 | Prem Watsa Fairfax | 0.696 | 35% | 34 | WBD 93% |
| 5 | Larry Robbins Glenview | 0.670 | 32% | 34 | AKAM 93% |
| 6 | Andreas Halvorsen Viking Global | 0.669 | 62% | 34 | HAS 92% |
| 7 | George Soros Soros Fund Mgmt | 0.663 | 50% | 34 | CON 99% |
| 8 | Lee Ainslie Maverick | 0.659 | 41% | 34 | EXEEZ 98% |
| 9 | Chase Coleman Tiger Global | 0.647 | 44% | 34 | XNDU 99% |
| 10 | Seth Klarman Baupost | 0.647 | 38% | 34 | V 92% |
| 11 | Stephen Mandel Lone Pine | 0.644 | 38% | 34 | TER 98% |
| 12 | Bruce Berkowitz Fairholme | 0.632 | 41% | 34 | AWM 97% |
| 13 | Howard Marks Oaktree | 0.626 | 44% | 34 | BILI 91% |
| 14 | Philippe Laffont Coatue | 0.615 | 41% | 34 | SOLS 81% |
| 15 | Brad Gerstner Altimeter | 0.612 | 35% | 34 | DNB 98% |
| 16 | Carl Icahn Icahn Capital | 0.610 | 38% | 34 | FNSR 82% |
| 17 | Renaissance Technologies Renaissance Technologies | 0.610 | 38% | 34 | BITA 5% |
| 18 | Chuck Akre Akre Capital | 0.606 | 56% | 34 | NOW 99% |
| 19 | David Einhorn Greenlight | 0.602 | 42% | 26 | ENR 91% |
| 20 | Ray Dalio Bridgewater | 0.595 | 35% | 34 | GOOG 99% |
| 21 | Chris Bloomstran Semper Augustus | 0.594 | 41% | 34 | BLDR 99% |
| 22 | Stanley Druckenmiller Duquesne | 0.589 | 44% | 34 | RVMD 97% |
| 23 | Tom Russo Gardner Russo & Quinn | 0.576 | 38% | 34 | SUNB 98% |
| 24 | Warren Buffett Berkshire Hathaway | 0.575 | 44% | 34 | GOOG 97% |
| 25 | David Abrams Abrams Capital | 0.562 | 26% | 34 | BID 47% |
| 26 | Francois Rochon Giverny | 0.559 | 53% | 34 | SUNB 99% |
| 27 | David Tepper Appaloosa | 0.537 | 53% | 34 | GKD 93% |
| 28 | Bill Ackman Pershing Square | 0.532 | 35% | 34 | MSFT 92% |
| 29 | Daniel Loeb Third Point | 0.530 | 47% | 34 | LITE 94% |
| 30 | Nelson Peltz Trian | 0.481 | 44% | 34 | NSY 77% |
| 31 | Mohnish Pabrai Dalal Street | 0.379 | 54% | 24 | PZZA 72% |
Below the line: not followed
A few high-turnover market-makers (Citadel, Millennium, D. E. Shaw, Point72) score high AUC because their 13Fs are huge churning books that are easy to predict but say little about conviction. They are marked below the line and left out of the followed consensus for that reason.
| Investor | Predict AUC | Quarters |
|---|---|---|
| D. E. Shaw D. E. Shaw | 0.803 | 34 |
| Izzy Englander Millennium | 0.779 | 34 |
| Ken Griffin Citadel | 0.775 | 34 |
| Steve Cohen Point72 | 0.620 | 34 |
AUC is out-of-sample walk-forward: each quarter is predicted using only earlier quarters. 0.50 is a coin flip. Beat-index is the share of backtested quarters the investor’s predicted top-10 beat the S&P 500 (gross, before costs). Samples are small and none of these per-investor edges is statistically significant. See how it works, calibration, and the methodology. Research, not investment advice.