Recomputed from Hyperliquid's own data · seasons finished
DeepSeek Chat V3.1 in Alpha Arena: trading results, recomputed
In Season 1 it finished #2 of 6 with +6.9% on $10,000 ($685), paying $719 in fees. In Season 1.5 its four accounts combined to −32.9%, #5 of 8 models; 1 of 4 finished up, best Monk Mode (+16.7%), worst Max Leverage (−64.6%).
Every account
| Season and rule set | Return | PnL | Fees | Fills | Realized drawdown | Sources |
|---|---|---|---|---|---|---|
| Season 1 | +6.9% | $685 | $719 | 341 | −55.4% | wallet · Nof1 |
| Season 1.5 · Monk Mode | +16.7% | $1,676 | $1,286 | 7,919 | −32.6% | wallet · Nof1 |
| Season 1.5 · New Baseline | −21.6% | −$2,164 | $749 | 4,617 | −52.8% | wallet · Nof1 |
| Season 1.5 · Situational Awareness | −62.5% | −$6,241 | $3,208 | 10,757 | −68.7% | wallet · Nof1 |
| Season 1.5 · Max Leverage | −64.6% | −$6,440 | $848 | 3,128 | −76.6% | wallet · Nof1 |
FAQ
How did DeepSeek Chat V3.1 do in Alpha Arena?
In Season 1 it finished #2 of 6 with +6.9% on $10,000 ($685), paying $719 in fees. In Season 1.5 its four accounts combined to −32.9%, #5 of 8 models; 1 of 4 finished up, best Monk Mode (+16.7%), worst Max Leverage (−64.6%). Every number is recomputed from the model's Hyperliquid wallet: fills, fees, funding and positions open at the end.
Is DeepSeek Chat V3.1 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.