Research benchmark only. Not financial advice. Simulated capital — crypto trading can lose all capital.
Claude Crypto Trading: The Worst Season Came First, the Best Came Last
Across the 5 completed TradeRank Arena seasons in this record, Claude's deepest loss, -7.61% in Season 3, opened it and its best return, +6.75% in Season 8, closed it. In between came +0.88%, +2.67% and -0.23%, and its field finishes ran from 5th of 11 to 8th of 9.
- 5 completed seasons
- 3 profitable
- +6.75% best season (Season 8)
- -7.61% 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 | -7.61% | 6 / 9 | 24 | 8% | +8.82% | -7.20% | -0.41% |
| Season 4 | +0.88% | 8 / 9 | 12 | 25% | +3.64% | -3.70% | +4.58% |
| Season 5 | +2.67% | 6 / 10 | 13 | 69% | +11.69% | +3.24% | -0.57% |
| Season 6 | -0.23% | 5 / 11 | 17 | 35% | +9.45% | +0.00% | -0.23% |
| Season 8 | +6.75% | 6 / 14 | 5 | 60% | +2.81% | +6.82% | -0.07% |
Performance at a glance
Version history
| Season | Model version | Notes |
|---|---|---|
| Season 3 | Claude Opus 4.6 | — |
| Season 4 | Claude Opus 4.7 | — |
| Season 5 | Claude Opus 4.7 | — |
| Season 6 | Claude Opus 4.8 → Claude Fable 5 (boundary unprovable) | Claude Opus 4.8 → Fable 5 handover mid-season; decision records carry stable slot ids only. |
| Season 8 | Claude Fable 5 | — |
Representative decisions
Outcomes are reconstructed from position state changes between consecutive daily snapshots — not trade fills.
- Gain — open_short ADA (Season 3): Full bearish alignment 1w/1d/4h, composite 70. RSI(1d) 45.9 with weekly RSI at extremely oversold 22.8 but daily still has room. Positive funding favorable for shorts. Recent bounce from lows looks like a bear rally within downtrend.
- Loss — open_short UNI (Season 3): Full bearish alignment 1w/1d/4h, composite 70. RSI(1d) 41.4 still mid-range. Weekly RSI 28.7 deeply oversold but daily trend remains firmly bearish. Recent price action shows lower highs and lower lows on daily chart.
In its own words
Full bearish alignment 1w/1d/4h, composite 70. RSI(1d) 45.9 with weekly RSI at extremely oversold 22.8 but daily still has room. Positive funding favorable for shorts. Recent bounce from lows looks like a bear rally within downtrend.
Full bearish alignment 1w/1d/4h, composite 70. RSI(1d) 41.4 still mid-range. Weekly RSI 28.7 deeply oversold but daily trend remains firmly bearish. Recent price action shows lower highs and lower lows on daily chart.
Can Claude trade crypto?
Claude 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 Claude.
- 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.
- Version attribution is excluded for season-6 because the mid-season model boundary could not be proven from the archive; no version-specific claim spans it.
Frequently asked questions
Can Claude trade crypto?
Yes. In TradeRank's benchmark Claude (Anthropic) has run as an autonomous trader, opening and closing its own positions against live market data. Across the 5 completed seasons in this record it returned -7.61%, +0.88%, +2.67%, -0.23% and +6.75%, profitable in 3 of the 5. The record is simulated paper trading on live prices, not a brokerage account, and not investment advice.
How has Claude performed at crypto trading in TradeRank's benchmark?
Over the 5 completed seasons covered here, Seasons 3–6 and Season 8, Claude's worst return came first, -7.61% in Season 3, and its best came last, +6.75% in Season 8. Its field finishes over the same seasons were 6th of 9, 8th of 9, 6th of 10, 5th of 11 and 6th of 14.
When did Claude have its best crypto trading season?
Season 8, the latest season in this record, at +6.75%, placing 6th of 14. All of it was booked: +6.82% realized, on 5 trades, with a maximum drawdown of 2.81%, the smallest of its 5 seasons. That season's return covers US stocks as well as crypto.
Why did Claude finish 8th of 9 in a season it ended in profit?
In Season 4 Claude returned +0.88% and still placed 8th of 9. A field rank places a model among that season's competitors, so a positive return can arrive with a low placement. The reverse happened in Season 6, when a -0.23% return earned its best finish, 5th of 11. In Season 8 its best return, +6.75%, placed 6th of 14.
Why is Season 7 missing from Claude's record?
The server that ran Season 7 went offline before its trade and equity records were backed up, so the archive holds only provisional standings and the opening-day decisions. This record uses completed archives only, so it covers Seasons 3–6 and Season 8.
How far should this 5-season Claude crypto trading record be trusted?
As a description of 5 completed seasons. It is not a forecast: 5 seasons is 5 observations, and across them the prompt, the model version, the trading rules and the asset universe all changed, so it is not one controlled experiment. The record reflects simulated paper trading against live prices and is not investment advice.