Grok Trading Bot Results: A Live Review of All 5 Grok Bots
Grok writes the trading rules for 5 bots on this site. We added Grok in July 2026 as the wildcard, because nobody knew how rulebooks it wrote would do. Here is each one's live record, as of the Sep 29, 2026 close.
One of them is #1 of 22 since start. Patience · Grok is +43.9% on paper from Jul 28, 2026 to the Sep 29, 2026 close. The S&P 500 did +3.4% over the same dates. Nearly all of it came early. From Jul 28 to the Aug 31 close it returned +41.0% on paper (S&P 500 +3.8%). From there to the Sep 29 close it returned +2.1% on paper (S&P 500 −0.4%). A strong few weeks can be luck.
Grok 4.7 has proposed the rewrites since Sep 22, 2026. Earlier Grok versions (4.20, then 4.5 and 4.6) did before that, so the older records span several versions.
About 20 bots trade in public on this site, each on its own $100,000 paper account, on real prices. Super Bot learns from all of them.
The Grok bots at a glance
| Bot | Since start, on paper | S&P 500, same dates | Rank |
|---|---|---|---|
| Patience · Grok since Jul 28, 2026 | +43.9% | +3.4% | #1 of 22 |
| Tactical · Grok since Aug 7, 2026 | +7.8% | −0.6% | #4 of 22 |
| Super Bot · Grok since Sep 2, 2026 | +5.9% | +0.3% | #8 of 22 |
| Weather-aware · Grok since Sep 2, 2026 | +2.2% | +0.3% | #15 of 22 |
| Super Bot Adaptive · Grok since Sep 21, 2026 | −0.6% | +0.3% | #19 of 22 |
Each bot, one by one
Patience · Grok #1 of 22 since start
Holds for days, not minutes, and only trades when it can name a reason.
- This month, Aug 31 close to Sep 29 close: +2.1% on paper, against −0.4% for the S&P 500.
- Worst dip from a high since start: 3.5%. Closed trades: 300.
Tactical · Grok #4 of 22 since start
Trades both ways: it buys, and it bets on stocks falling when a setup breaks down.
- This month, Aug 31 close to Sep 29 close: −2.7% on paper, against −0.4% for the S&P 500.
- Worst dip from a high since start: 6.8%. Closed trades: 305.
Super Bot · Grok #8 of 22 since start
Learns from every other bot: each morning it rewrites its rules from yesterday's trades, its own notes, and the best rules other bots have proven. Trades both ways.
- It started on Sep 2, 2026, so its figure for this month is its whole record so far.
- Worst dip from a high since start: 1.9%. Closed trades: 182.
Weather-aware · Grok #15 of 22 since start
The Patience rules, plus smaller bets on jumpy stocks and a picker that switches to saved rulebooks that suited this kind of market before.
- It started on Sep 2, 2026, so its figure for this month is its whole record so far.
- Worst dip from a high since start: 4.2%. Closed trades: 229.
Every Weather-aware · Grok trade
Super Bot Adaptive · Grok #19 of 22 since start
A practice-money twin of Super Bot that adds extra caution: smaller bets when the market looks shaky, and it drops setups that have stopped working.
- It started on Sep 21, 2026, so its figure for this month is its whole record so far.
- Worst dip from a high since start: 0.8%. Closed trades: 70.
Every Super Bot Adaptive · Grok trade
What this does and doesn't show
- Practice money. Paper accounts, real prices. Nobody earned these figures, and they are before trading costs.
- Short windows flatter or punish. 3 of these 5 started this month. A few good or bad weeks can swing a short record either way.
- The market's mood. The S&P 500 rose 5.3% from the Jul 24 close to its Aug 13 high, then chopped sideways (at worst 3.1% below that high) and ended Sep 29 1.8% below it. Our market-weather reading for Sep 29 was "choppy". Bots that started in late July caught the climb. September starters did not.
- The AI matters, and so does the brief. The same "Patience" brief runs under 4 AIs. On paper, to the Sep 29 close: Patience · Grok +43.9% since Jul 28 (S&P 500 +3.4%); Patience · Claude +24.7% since Jul 27 (S&P 500 +3.4%); Patience · ChatGPT +15.8% since Jul 27 (S&P 500 +3.4%); Patience · Gemini +2.2% since Aug 4 (S&P 500 +0.9%). Tactical, a second shared brief, runs from +7.8% (Tactical · Grok) to −1.5% (Tactical · Gemini) on paper since Aug 7, against −0.6% for the S&P 500.
- One of these is copied with real money. A small real-money account run by the site's operator has copied Super Bot · Grok since Sep 14, 2026. Its results, after real fees, are on the Real money page. Everything else here is paper.
- Not a prediction. Nothing here says what any bot will do next, or that Grok is good or bad at trading.
HYPOTHETICAL OR SIMULATED PERFORMANCE RESULTS HAVE CERTAIN LIMITATIONS. UNLIKE AN ACTUAL PERFORMANCE RECORD, SIMULATED RESULTS DO NOT REPRESENT ACTUAL TRADING. ALSO, SINCE THE TRADES HAVE NOT BEEN EXECUTED, THE RESULTS MAY HAVE UNDER- OR OVER-COMPENSATED FOR THE IMPACT, IF ANY, OF CERTAIN MARKET FACTORS, SUCH AS LACK OF LIQUIDITY. SIMULATED TRADING PROGRAMS IN GENERAL ARE ALSO SUBJECT TO THE FACT THAT THEY ARE DESIGNED WITH THE BENEFIT OF HINDSIGHT. NO REPRESENTATION IS BEING MADE THAT ANY ACCOUNT WILL OR IS LIKELY TO ACHIEVE PROFITS OR LOSSES SIMILAR TO THOSE SHOWN. See the risk disclosure.
Follow a bot
Get one email a day about any bot, after the close. Quiet days included.
Follow a bot — one email a day
Or watch every bot on the live scoreboard, or see Grok's bots side by side on the Grok record page.
FAQ
- Does this show Grok is good at trading?
- No. It shows how rulebooks Grok wrote did on paper over a short stretch that was mostly rising, then choppy. A different stretch could look very different.
- Why isn't The Learner · filtered listed?
- The scoreboard files The Learner · filtered under Grok for bookkeeping, but no AI writes its rules. It runs System's fixed rules with a filter that learns from past trades, so this page leaves it out. Its record page is public.
See the live scoreboard — free
These are paper trades — simulated money, real market prices — published as a record of what happened, not as advice and not as a prediction. Nothing here is a recommendation or a forecast, and no figure on this page describes money anyone earned or could have earned.
More from The AI Trading Competition
More than twenty trading bots — most rewritten daily by four AI models, a few never — ranked by paper return against the S&P 500 in the Bot Analysis Arena.
- How the AI Trading Competition works — methodology & transparency — the pillar page for this series.
- The Bot Analysis Arena — every bot's current return
- The public record — every bot's paper returns, by AI model
- The rulebook — how a trade is opened, sized and closed
- Claude Trading Bot Results: A Live Review of All 5 Claude Bots
- ChatGPT vs Claude Trading — Live Head-to-Head, Every Trade Public
- Can AI Beat the Stock Market? (We're Testing It Live)
- ChatGPT vs Claude vs Grok — one live arena: trading, chess, and poker
- Gemini Trading Bot: The Live Paper Record of Both Gemini Bots