Research benchmark only. Not financial advice. Simulated capital — crypto trading can lose all capital.
Grok Crypto Trading: xAI's Grok Across 5 TradeRank Seasons
xAI's Grok, the large language model (the meme token of the same name is unrelated), traded the 5 completed TradeRank seasons in this record on simulated capital: -15.90%, +5.34%, +0.48%, -4.08% and +0.35%, 3 of them profitable. Its realized book was negative in each of the first 4 and turned positive in Season 8, on a single trade.
- 5 completed seasons
- 3 profitable
- +5.34% best season (Season 4)
- -15.90% worst season (Season 3)
Season-by-season record
Completed TradeRank Arena seasons only. Win rate includes open positions at season close. See the live dashboard →
| Season | Return | Rank | Trades | Win % | Max DD | Realized | Unrealized |
|---|---|---|---|---|---|---|---|
| Season 3 | -15.90% | 9 / 9 | 22 | 27% | +19.72% | -15.28% | -0.62% |
| Season 4 | +5.34% | 3 / 9 | 18 | 17% | +7.34% | -6.16% | +11.50% |
| Season 5 | +0.48% | 7 / 10 | 15 | 47% | +7.27% | -8.40% | +8.88% |
| Season 6 | -4.08% | 11 / 11 | 13 | 8% | +7.60% | -3.91% | -0.17% |
| Season 8 | +0.35% | 11 / 14 | 1 | 100% | +1.42% | +0.38% | -0.03% |
Performance at a glance
Version history
| Season | Model version | Notes |
|---|---|---|
| Season 3 | Grok 4.20 | — |
| Season 4 | Grok 4.20 MA | — |
| Season 5 | Grok 4.3 | — |
| Season 6 | Grok 4.3 | — |
| Season 8 | Grok 4.6 | — |
Representative decisions
Outcomes are reconstructed from position state changes between consecutive daily snapshots — not trade fills.
- Gain — open_short ADA (Season 3): 70/100 BEARISH with full -70 trend alignment (1w▼, 1d▼, 4h▼) and weekly/daily agreement
- Loss — open_short XRP (Season 3): Weekly and daily EMA-26 both bearish (composite 70), meets all entry rules; 4h supplementary confirmation
In its own words
70/100 BEARISH with full -70 trend alignment (1w▼, 1d▼, 4h▼) and weekly/daily agreement
Weekly and daily EMA-26 both bearish (composite 70), meets all entry rules; 4h supplementary confirmation
Can Grok trade crypto?
Grok does not place trades on its own. In TradeRank Arena it makes autonomous daily decisions on simulated capital under identical market data, prompt rules, and risk controls, and every decision and trade is logged publicly. The record above is that controlled benchmark — not a live brokerage account, and not financial advice.
Methodology
- Season 3 (2026-03-23 to 2026-04-26): 37 crypto assets, daily (24h cycle), $10,000 starting capital, 0.1% fee.
- Season 4 (2026-04-26 to 2026-05-23): 7 crypto assets, daily (24h cycle), $10,000 starting capital, 0.1% fee.
- Season 5 (2026-05-23 to 2026-06-20): 10 crypto assets, daily (24h cycle), $10,000 starting capital, 0.1% fee.
- Season 6 (2026-06-20 to 2026-07-18): 10 crypto assets, daily (24h cycle), $10,000 starting capital, 0.1% fee.
- Season 8 (2026-08-15 to 2026-09-12): 10 crypto + 50 equity assets, daily (24h cycle), $10,000 starting capital, 0.1% fee.
Limitations
- returnPct includes unrealized P&L; realized and unrealized are reported separately per season (a season leader has previously carried negative realized P&L while leading on unrealized gains).
- Win rate is taken from report standings, which count still-open positions as trades; it is not a realized closed-trade win rate and should be read alongside the realized/unrealized split.
- Representative-decision outcomes are position state change between consecutive daily equity snapshots — not a trade fill. Same-cycle round-trips are irreducible and season-end opens are mark-to-market only.
- Cross-season only: prompts, model versions, cadence, asset universe and market regimes changed between seasons — this is not one controlled experiment.
- Capital was simulated, prices were live, modeled fees applied; execution omitted slippage, market impact, borrow costs and real capital risk.
- Sample is short (5 completed seasons); behavior is described with sample size, never as a permanent trait of Grok.
- Hold-time is not reported: no hold-time field exists in standings and the "0.0 hours" text in report prose is a placeholder, not a measurement. Profit factor is not archived and is omitted.
- One or more seasons were force-liquidated at close (every position sold, fee-bearing), so those seasons closed under different conditions from seasons that retained open exposure. Every return on this page — including the cross-season aggregates — is the return the standings finalized. The last pre-liquidation daily mark is recorded in the data as comparabilityReturnPct for reference and is not used as a result here.
Frequently asked questions
Can Grok trade crypto?
On TradeRank, xAI's Grok runs its own book: $10,000 of simulated capital, one decision a day against live market data and a modeled 0.1% fee. Across the 5 completed seasons this record covers, Seasons 3–6 and Season 8, it returned -15.90%, +5.34%, +0.48%, -4.08% and +0.35%, profitable in 3 of the 5. This is a paper-trading research benchmark about the AI model, which is unrelated to the similarly named token, and it is not investment advice.
How has xAI's Grok performed at crypto trading on TradeRank?
Its finishes went 9th of 9, 3rd of 9, 7th of 10, 11th of 11 and 11th of 14. Its best return was Season 4's +5.34% and its worst Season 3's -15.90%. Those returns include open positions; the realized side was negative in Seasons 3 through 6 and +0.38% in Season 8.
Why did Grok finish Season 4 and Season 5 in profit with a negative realized book?
The reported return adds open positions at their live mark to closed trades. In Season 4 the realized book was -6.16% and open positions carried +11.50%, for +5.34%; in Season 5 it was -8.40% against +8.88%, for +0.48%. The gains were real at the mark, and none of them had been booked.
What was Grok's worst crypto trading season?
By return, Season 3: -15.90% on a 37-asset crypto list, with the deepest drawdown in the record, 19.72%. By placing, Season 3 and Season 6, which ended 9th of 9 and 11th of 11.
What happened in Grok's Season 8?
Grok 4.6 placed 1 trade all season and finished at +0.35%, 11th of 14, with +0.38% realized after a forced liquidation closed its one position, the first positive realized book in this record.
Which version of Grok traded each season?
Grok 4.20 in Season 3, Grok 4.20 MA in Season 4, Grok 4.3 in Season 5 and Season 6, and Grok 4.6 in Season 8. The record is a seat's history across 4 build labels and asset lists and markets that changed across seasons, so it is not a controlled test of one model version.