Research benchmark only. Not financial advice. Crypto trading can lose all capital.
AI Trading Dogecoin: 25 LLMs, 329 Trades, 3 Seasons
Dogecoin is the position nobody expects anyone to defend, and its closed record is in the black. What tipped it was not the early churn but the most recent season with a surviving log, where a far wider field traded DOGE and finished ahead.
Kimi K3 holds the strongest aggregate realized result on Dogecoin: $266.26, on a single closed trade. That is one asset's record, not an overall ranking — 25 models have traded a DOGE position here, over 3 seasons whose trade log survives.
- 329DOGE trades on record (floor)
- 170closed with a realized result
- $962.09realized, all models combined
- 0open positions in the live season
Best LLM for Trading Dogecoin
This ranking answers one narrow question — who realized a gain on DOGE — and the rows underneath it show whether an entry came from a single good season or from repeated work across the archive.
Kimi K3 — $266.26 realized on DOGE
1 closed leg of 1 trade, in Season 6.
GLM-5.2 and Grok 4.5, joint at $199.70 realized on DOGE
GLM-5.2 on 1 closed leg of 2 trades, in Season 6; Grok 4.5 on 1 closed leg of 1 trade, in Season 6.
Nemotron 3 Ultra — $133.13 realized on DOGE
1 closed leg of 2 trades, in Season 6.
Ranked by aggregate realized profit and loss on DOGE alone, over the seasons whose trade log survives. Equal results are joint, never ordered. Open positions carry no realized figure and are excluded.
Can AI Trade Dogecoin?
They do, frequently, and mostly in momentum language: breakouts, volume, and what the rest of the market is doing. Whether that amounts to a Dogecoin strategy is a fair question, and the quotes let you decide it directly.
25 model versions have executed a DOGE trade in TradeRank, and 39 versions have traded it or written about it in their decisions. The realized total across every closed leg is $962.09, and that total is a floor rather than a count.
Every Model's DOGE Record
One row per model version. A cell reads n/a where the answer is unknown: the trade log for those seasons did not survive. A known zero is shown as a zero instead — a row that traded and closed nothing realized nothing, which is a measurement rather than a gap.
| Model | Provider | Trades | Closed | Realized P&L | Seasons |
|---|---|---|---|---|---|
| Kimi K3 | Moonshot | 1 | 1 | $266.26 | Season 6 |
| GLM-5.2 | Zhipu AI | 2 | 1 | $199.70 | Season 6 |
| Grok 4.5 | xAI | 1 | 1 | $199.70 | Season 6 |
| Nemotron 3 Ultra | NVIDIA | 2 | 1 | $133.13 | Season 6 |
| Claude Opus 4.8 | Anthropic | 3 | 1 | $131.20 | Season 6 |
| DeepSeek V4 Pro | DeepSeek | 5 | 2 | $119.92 | Season 6 |
| Gemini 3 Pro | 10 | 5 | $116.54 | Season 1 | |
| GPT-5.6 | OpenAI | 1 | 1 | $113.75 | Season 6 |
| MiniMax M3 | MiniMax | 2 | 1 | $112.57 | Season 6 |
| Qwen 3.7 Plus | Alibaba | 3 | 1 | $107.67 | Season 6 |
| Gemini 3.5 Flash | 2 | 1 | $59.95 | Season 6 | |
| Qwen 3.7 Max | Alibaba | 1 | 1 | $36.46 | Season 6 |
| Mistral Medium 3.5 | Mistral AI | 2 | 1 | $26.96 | Season 6 |
| Grok 4-1 Fast | xAI | 44 | 22 | $5.41 | Seasons 0 and 1 |
| GPT-5.5 | OpenAI | 1 | 0 | $0.00 | Season 6 |
| Grok 4.1 Fast | xAI | 0 | 0 | $0.00 | — |
| Grok 4.3 | xAI | 1 | 0 | $0.00 | Season 6 |
| Kimi K2.7 Code | Moonshot | 1 | 0 | $0.00 | Season 6 |
| MiniMax M2.5 | MiniMax | 0 | 0 | $0.00 | — |
| o4-mini | OpenAI | 22 | 12 | -$19.51 | Season 1 |
| Claude Haiku 4.5 | Anthropic | 22 | 11 | -$36.12 | Season 1 |
| Claude Fable 5 | Anthropic | 1 | 1 | -$36.49 | Season 6 |
| Qwen3 | Alibaba | 57 | 30 | -$54.78 | Season 1 |
| Gemini 2.5 Flash | 21 | 10 | -$66.16 | Seasons 0 and 1 | |
| GPT-5 Mini | OpenAI | 53 | 31 | -$72.16 | Seasons 0 and 1 |
| Kimi K2 | Moonshot | 28 | 12 | -$167.72 | Season 1 |
| DeepSeek R1 | DeepSeek | 43 | 23 | -$214.17 | Season 1 |
| Claude Opus 4.6 | Anthropic | n/a | n/a | n/a | Season 3 |
| Claude Opus 4.7 | Anthropic | n/a | n/a | n/a | Seasons 4 and 5 |
| DeepSeek V3.2 | DeepSeek | n/a | n/a | n/a | Season 3 |
| Gemini 3.1 Pro | n/a | n/a | n/a | Seasons 3 and 4 | |
| GLM-5.1 | Zhipu AI | n/a | n/a | n/a | Seasons 4 and 5 |
| Grok 4.20 | xAI | n/a | n/a | n/a | Season 3 |
| Grok 4.20 MA | xAI | n/a | n/a | n/a | Season 4 |
| Kimi K2.5 | Moonshot | n/a | n/a | n/a | Season 3 |
| Kimi K2.6 | Moonshot | n/a | n/a | n/a | Seasons 4 and 5 |
| MiniMax M2.7 | MiniMax | n/a | n/a | n/a | Seasons 4 and 5 |
| Qwen 3.5 Plus | Alibaba | n/a | n/a | n/a | Season 3 |
| Qwen 3.6 Plus | Alibaba | n/a | n/a | n/a | Seasons 4 and 5 |
Dogecoin AI Trading Performance by Season
Dogecoin's two logged eras point in opposite directions. The early one bled, the later one paid, and the later one had roughly twice as many model versions putting money into DOGE.
Trade counts are not comparable across the whole column: the early seasons ran several decision cycles a day and the later ones settle everything at one fixed hour, so the Cycle column states which regime each row belongs to.
| Season | Cycle | Trades | Closed | Realized P&L | Models trading |
|---|---|---|---|---|---|
| Season 0 | intraday | 18 | 8 | -$9.93 | 3 |
| Season 1 | intraday | 282 | 148 | -$498.75 | 9 |
| Season 2 | intraday | 0 | 0 | $0.00 | 0 |
| Season 3 | once daily | n/a | n/a | n/a | n/a |
| Season 4 | once daily | n/a | n/a | n/a | n/a |
| Season 5 | once daily | n/a | n/a | n/a | n/a |
| Season 6 | once daily | 29 | 14 | $1,470.77 | 16 |
A cell reads n/a where the answer is unknown: the trade log for those seasons did not survive. A known zero is shown as a zero instead — a row that traded and closed nothing realized nothing, which is a measurement rather than a gap.
Who Holds DOGE Right Now
The season now running, as of the last completed cycle. Every table above this block is frozen archive; this block and the fourth figure in the hero are the only parts that move.
No model is holding DOGE in the current season. That is a real reading of the book, not a missing feed: the season has recorded 0 DOGE trades so far.
Season so far: 0 trades, 0 closed legs, realized n/a. The live leaderboard carries the current standings.
The Best and Worst DOGE Calls
Selected deterministically from the trade log: the strongest and weakest closed DOGE legs that carry a written rationale, whichever model made them. A larger leg with no reasoning attached to it is not shown here, because the section exists to publish the reasoning.
Largest quoted DOGE leg: $131.20, Claude Opus 4.8
Daily RSI 27.5 deeply oversold, 1h bouncing strongly. +8.8% profit — take it to reduce relief-rally risk while trend still bearish.
Weakest quoted DOGE leg: -$81.57, DeepSeek R1
Stop loss at 0.1024 has been triggered with current price at 0.10158. Closing to limit further losses in a bearish market.
What the Models Said About Dogecoin
Every quote below is a model's own reasoning for a DOGE decision, unedited apart from length. Selection is deterministic and recorded in the pack.
Daily RSI 27.5 deeply oversold, 1h bouncing strongly. +8.8% profit — take it to reduce relief-rally risk while trend still bearish.
The short has reached the 0.07 support target zone with an 11.5% gain, making further downside less attractive as daily momentum becomes stretched.
Short captured +11.4% on decline from $0.0837 to $0.0741; DOGE weekly RSI 33 indicates deeply oversold conditions with bounce risk rising - lock in gains and redeploy capital.
Daily trend reversing up for 2+ candles against the short; composite score < 50 mandates staying flat.
4h has flipped bullish (EMA-26 above), creating timeframe conflict with weekly/daily bearish alignment. Per strategy exit rules, close when lower timeframe contradicts and daily has not held bearish for 2+ candles with…
Closing short to secure remaining profits as daily indicators shift heavily bullish, signaling trend reversal.
Bounce has persisted with 4h RSI 62 and BTC pressing range highs — short thesis effectively invalidated, cutting the loss before a BTC breakout accelerates it.
DOGE short profitable but losing momentum; RSI_1d at 41.65 suggests consolidation, reducing upside for short. Prefer to free capital for higher-conviction plays.
Full bearish alignment across weekly, daily, and 4h; composite 70/100. RSI 34.0 confirms a weak down-move rather than a bearish rally, favoring trend-following shorts.
Full bearish alignment across all timeframes with composite 70. Daily RSI at 34.0 confirms strong downside momentum. Weekly candle shows rejection from 0.092 highs with close at 0.084.
Weekly and daily both below EMA-26 (bearish), composite 70, daily RSI 34.0 supports
Weekly/daily/4h EMA-26 all bearish (score 70). Negative Binance funding (-0.0045%) benefits shorts. RSI 34 not overbought but trend alignment strong.
DOGE has full weekly, daily and 4h bearish EMA alignment with a 70/100 bearish score; position is kept at minimum size because daily RSI is already low, increasing bounce risk.
Thesis unchanged—price continues print lower under broken multi-month structure and weekly RSI remains depressed at 33 supporting further weakness over weeks.
Bearish weekly/daily alignment intact with composite 70; profitable trend continuation
70/100 bearish, daily RSI 34.3 oversold but trend intact; adding to existing short.
Score 70 bearish alignment intact; daily momentum continues downward with RSI at 34 indicating room for further extension.
Strong profit at +14.9%, composite 70 bearish, weekly trend intact. Recent daily candles only marginally bullish, no reversal signal.
Weekly, daily and 4h all remain bearish with composite score 70, so the trend-following short remains valid.
Composite 70 BEARISH. Full timeframe alignment (1w/1d/4h all below EMA-26). Daily RSI 34.3 confirms downtrend momentum, weekly RSI 33 shows persistent weakness.
Weekly (▼30) and daily (▼25) EMAs bearish. RSI(1d)=34.3 oversold but no reversal. Composite=70 BEARISH. Hold short.
DOGE scores 70/100 BEARISH with perfect weekly/daily/4h alignment (all bearish). Daily RSI at 34.3 approaching oversold but not yet there, suggesting continuation potential. Funding rate favorable at 0.0004%.
Short up 15.5% with full bearish alignment. Weekly RSI 33, daily RSI 33 — oversold but trend unbroken. Holding for trend continuation.
Aligned bearish trend (70/100) and daily RSI at 33.1 support continued short exposure. Price structure respects the ongoing downtrend.
What This Page Does and Does Not Measure
- Trade records cover Seasons 0, 1 and 6. Seasons 3, 4 and 5 ran Dogecoin but their trade logs are unrecoverable, so those rows read n/a.
- Season 1 survives only as a partial log, so every all-time total on this page is a floor rather than a count.
- Decision reasoning covers Seasons 1, 2, 3, 4, 5 and 6, which is why a model can be quoted in a season with no trades beside it.
- 35.9% of the 170 closed DOGE legs finished positive. This is a closed-trade rate on this asset only. It is not the standings win rate, which counts open positions too, and the two are not comparable in either direction.
- Everything here is paper trading. Each model starts from the same simulated balance, pays a fee on every fill, and risks no capital. How the competition works.
Dogecoin AI Trading — FAQ
What is the best LLM for trading Dogecoin?
Kimi K3 holds the strongest aggregate realized result on DOGE: $266.26, on a single closed trade. That is one asset's record, not an overall ranking, and it covers only the seasons whose trade log survives.
Can AI trade Dogecoin?
They already do. 25 models have executed 329 DOGE trades in TradeRank, 170 of them closed with a realized result.
How many AI models have traded DOGE?
25 model versions have executed a DOGE trade. A wider set — 39 versions — traded it or wrote about it in their decisions, including seasons whose trade log did not survive.
Did the models make or lose money on Dogecoin?
Across the closed DOGE trades on record the realized total is $962.09. Season 1 survives only as a partial log, so that is a floor. Open positions carry no realized figure and are not in that total.
Which seasons does this Dogecoin record cover?
Trades: Seasons 0, 1 and 6. Seasons 3, 4 and 5 ran the asset but their trade logs are unrecoverable, so those rows read n/a rather than zero.
Are the Dogecoin results on this page live trades?
No. TradeRank is a paper-trading benchmark: each model starts from the same simulated balance, pays fees on every fill, and risks no capital.