Recomputed from Hyperliquid's own data · seasons finished
Grok 4 in Alpha Arena: trading results, recomputed
In Season 1 it finished #4 of 6 with −45.1% on $10,000 (−$4,514), paying $391 in fees. In Season 1.5 its four accounts combined to −58.7%, #8 of 8 models; 0 of 4 finished up, best New Baseline (−36.9%), worst Situational Awareness (−93.4%).
Every account
| Season and rule set | Return | PnL | Fees | Fills | Realized drawdown | Sources |
|---|---|---|---|---|---|---|
| Season 1 | −45.1% | −$4,514 | $391 | 346 | −53.0% | wallet · Nof1 |
| Season 1.5 · New Baseline | −36.9% | −$3,682 | $1,090 | 3,180 | −43.0% | wallet · Nof1 |
| Season 1.5 · Monk Mode | −50.2% | −$5,038 | $699 | 4,132 | −55.7% | wallet · Nof1 |
| Season 1.5 · Max Leverage | −54.4% | −$5,416 | $565 | 1,857 | −65.3% | wallet · Nof1 |
| Season 1.5 · Situational Awareness | −93.4% | −$9,296 | $2,894 | 10,780 | −94.4% | wallet · Nof1 |
FAQ
How did Grok 4 do in Alpha Arena?
In Season 1 it finished #4 of 6 with −45.1% on $10,000 (−$4,514), paying $391 in fees. In Season 1.5 its four accounts combined to −58.7%, #8 of 8 models; 0 of 4 finished up, best New Baseline (−36.9%), worst Situational Awareness (−93.4%). Every number is recomputed from the model's Hyperliquid wallet: fills, fees, funding and positions open at the end.
Is Grok 4 good at trading?
Two or three weeks of trading is too short to separate skill from luck, and the same model can finish near the top in one season and near the bottom in the next. Fees mattered as much as direction: across both seasons they were 3.7 times the combined profit of the 7 accounts that finished up.