Latest change
Correction
The arena restated its record: source normalization restated 58
Qwen3.7 Max
RunsQwen3.7 Max
You're looking at the performance of this whole trading setup (the AI model plus its prompts, rules and risk settings, run by Clash of AIs), not a laboratory test of the AI model by itself.
Recorded as it happened, but not independently verified: the arena runs these paper accounts itself, so TBT can't rebuild the result on its own.
Data observed from Clash of AIs' free public interface. Clash of AIs publishes no explicit data licence. Trading Bot Tracker is independent and is not affiliated with or endorsed by Clash of AIs.
Return since the run started on 9 Apr 2026
+1.74%
Paper money, not real cash · 9 Apr 2026 to 5 Oct 2026 (179 days) · counted under Clash of AIs' rules · not independently verified
TBT-observed · 5 Oct 13:51 UTC · 8f121b2f- Running since
- 9 Apr 2026179 days, as the arena reports
- TBT watching since
- 3 Oct 20262 days · 6 observations
In its fair comparison
11th of 13
Change over the last 30 days, % of the starting account: −0.32%, among comparable Clash of AIs bots. Describes past observations, not future results. Not a recommendation.
- Account value
- $101,738.17
- Started with
- $100,000.00
- Trades (arena's count)
- 661 still open
- Arena's own list
- #17 of 19
Paper (simulated) accounts starting at $100,000, counted before fees and costs. Leverage is simulated without forced closes (5x when a signal states none), so an account can fall below −100%. Since 22 Jul 2026 the operator has multiplied position sizes by 10.
- Return
- +1.74% since 9 Apr
- Fair comparison
- 11th of 13 Change over the last 30 days, % of the starting account
- Largest fall from a high
- 1.5% of the starting account 4 Aug to 11 Sep, arena history
- Running
- 179 days since 9 Apr
- TBT watching
- 2 days 6 observations
- Evidence
- FORWARD_TESTED
Something in the record
Its five biggest winners made 87% of all its closed-trade gains, out of 25 winning trades.
From Clash of AIs' own figures for every closed trade TBT preserved.
See how it got hereThe run so far
- TBT-observed seen by TBT itself
- Source-reported Clash of AIs' published history
- Biggest trades where they closed
TBT has observed this run 6 times since 3 Oct 2026, most recently at +1.74%. Before that, Clash of AIs published its own history back to 9 Apr 2026, drawn as a faint line. Clash of AIs' history tracks the account balance, while TBT records the account value, which also counts trades still open, so the two lines can differ a little.
Trade evidence
How it got here
Where this result came from: the 66 trades Clash of AIs closed in this run, as TBT preserved them, ranked by Clash of AIs' own dollar result. These are paper trades: the dollar figures are simulated, not cash anyone earned or lost. Below are the 5 biggest gains and 5 biggest losses: open any of them to see exactly what happened.
- Closed trades
- 66
- Won / lost
- 25 / 38 40% won
- Total from closed trades
- +$1,615 paper money, Clash of AIs' own figures
- Biggest win
- +$1,674 36% of all the gains
- Biggest loss
- −$1,538
It made more than it lost: 25 winning trades made $4,615, and 38 losing trades gave back $3,000. A few big winners did most of the work: the top 5 trades made 87% of all the gains.
Why this isn't exactly the headline number. The closed trades add up to +$1,615. Clash of AIs' own account balance changed by +$650.36 over the run, and the account value behind the headline +1.74%, which also counts 1 trade still open, by +$1,738.17. The trades and the balance don't reconcile exactly: a gap of +$964.64 that the published trades don't explain. TBT shows the gap rather than assigning it to any trade.
Best trades
Biggest gains first. Sizes and dollar results are Clash of AIs' own figures.
MSFT/USDTLong+$1,674 · +3.37%
- Opened
- 2026-08-01 01:03 UTC
- Closed
- 2026-08-04 21:55 UTC
- Traded
- MSFT/USDT
- Direction
- Long (a bet the price would rise)
- Entry
- 465
- Exit
- 490
- Stop
- 445
- Targets
- 472,480,490 · 3 hit
- Leverage
- 5x
- Size
- $9,940 of paper money (10% of the account) Clash of AIs' figure
- Result
- +$1,674 · +3.37% Clash of AIs' figure
- How it ended
- All targets hit
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- 41f18dff…
AAPL/USDTLong+$1,218 · +2.45%
- Opened
- 2026-09-11 01:50 UTC
- Closed
- 2026-09-23 02:04 UTC
- Traded
- AAPL/USDT
- Direction
- Long (a bet the price would rise)
- Entry
- 327
- Exit
- 339
- Stop
- 316
- Targets
- 331,335,339 · 3 hit
- Leverage
- 5x
- Size
- $9,953 of paper money (10% of the account) Clash of AIs' figure
- Result
- +$1,218 · +2.45% Clash of AIs' figure
- How it ended
- All targets hit
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- bd248347…
MSFT/USDTLong+$868 · +1.72%
- Opened
- 2026-08-05 03:19 UTC
- Closed
- 2026-09-07 05:53 UTC
- Traded
- MSFT/USDT
- Direction
- Long (a bet the price would rise)
- Entry
- 493
- Exit
- 499.7
- Stop
- 478
- Targets
- 505,515,530 · 1 hit
- Leverage
- 5x
- Size
- $10,107 of paper money (10% of the account) Clash of AIs' figure
- Result
- +$868 · +1.72% Clash of AIs' figure
- How it ended
- Expired
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- a69bfd5a…
BTC/USDTLong+$131 · +2.61%
- Opened
- 2026-06-12 17:56 UTC
- Closed
- 2026-06-15 12:46 UTC
- Traded
- BTC/USDT
- Direction
- Long (a bet the price would rise)
- Entry
- 63,832
- Exit
- 66,500
- Stop
- 62,500
- Targets
- 64500,65000,65500,66000,66500 · 5 hit
- Leverage
- 5x
- Size
- $1,001 of paper money (1% of the account) Clash of AIs' figure
- Result
- +$131 · +2.61% Clash of AIs' figure
- How it ended
- All targets hit
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- bad1b74e…
BTC/USDTShort+$114 · +2.28%
- Opened
- 2026-06-23 12:26 UTC
- Closed
- 2026-06-24 16:51 UTC
- Traded
- BTC/USDT
- Direction
- Short (a bet the price would fall)
- Entry
- 62,353
- Exit
- 60,000
- Stop
- 63,600
- Targets
- 61800,61000,60000 · 3 hit
- Leverage
- 5x
- Size
- $1,000 of paper money (1% of the account) Clash of AIs' figure
- Result
- +$114 · +2.28% Clash of AIs' figure
- How it ended
- All targets hit
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- a9719a9a…
Worst trades
Biggest losses first. Sizes and dollar results are Clash of AIs' own figures.
NVDA/USDTLong−$1,538 · −3.04%
- Opened
- 2026-09-07 05:54 UTC
- Closed
- 2026-09-11 01:46 UTC
- Traded
- NVDA/USDT
- Direction
- Long (a bet the price would rise)
- Entry
- 230
- Exit
- 223
- Stop
- 223
- Targets
- 236,242,249
- Leverage
- 5x
- Size
- $10,107 of paper money (10% of the account) Clash of AIs' figure
- Result
- −$1,538 · −3.04% Clash of AIs' figure
- How it ended
- Stop hit
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- 951931f0…
NVDA/USDTShort−$229 · −4.59%
- Opened
- 2026-06-26 10:21 UTC
- Closed
- 2026-07-13 07:30 UTC
- Traded
- NVDA/USDT
- Direction
- Short (a bet the price would fall)
- Entry
- 196
- Exit
- 205
- Stop
- 205
- Targets
- 191,185,179
- Leverage
- 5x
- Size
- $999 of paper money (1% of the account) Clash of AIs' figure
- Result
- −$229 · −4.59% Clash of AIs' figure
- How it ended
- Stop hit
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- 081a80b0…
META/USDTLong−$186 · −3.73%
- Opened
- 2026-07-13 07:30 UTC
- Closed
- 2026-07-21 21:49 UTC
- Traded
- META/USDT
- Direction
- Long (a bet the price would rise)
- Entry
- 670
- Exit
- 645
- Stop
- 645
- Targets
- 685,705,730
- Leverage
- 5x
- Size
- $997 of paper money (1% of the account) Clash of AIs' figure
- Result
- −$186 · −3.73% Clash of AIs' figure
- How it ended
- Stop hit
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- f71b724c…
BTC/USDTLong−$180 · −3.60%
- Opened
- 2026-06-25 10:18 UTC
- Closed
- 2026-06-25 13:48 UTC
- Traded
- BTC/USDT
- Direction
- Long (a bet the price would rise)
- Entry
- 61,719
- Exit
- 59,500
- Stop
- 59,500
- Targets
- 63200,64800,66500
- Leverage
- 5x
- Size
- $1,001 of paper money (1% of the account) Clash of AIs' figure
- Result
- −$180 · −3.60% Clash of AIs' figure
- How it ended
- Stop hit
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- 971db309…
AAPL/USDTLong−$137 · −2.74%
- Opened
- 2026-07-21 21:53 UTC
- Closed
- 2026-08-01 01:00 UTC
- Traded
- AAPL/USDT
- Direction
- Long (a bet the price would rise)
- Entry
- 328
- Exit
- 311
- Stop
- 311
- Targets
- 335,342,350 · 1 hit
- Leverage
- 5x
- Size
- $995 of paper money (1% of the account) Clash of AIs' figure
- Result
- −$137 · −2.74% Clash of AIs' figure
- How it ended
- Stop hit after 1 target
- AI model when opened
- Qwen3.7 Max (era start not reported)
- Clash of AIs trade id
- ed1e4e13…
These are the extremes, not typical trades. Half of its 66 closed trades ended between −0.32% and +0.26%.
Observed behavior
Measurements of the recorded closed trades, not a description of a personality or a strategy. Closed trades don't cover everything the account did: open positions aren't included.
- Long or short
- 94% of its 66 recorded closed trades were long, 6% short.
- Most-traded pair
- BTC/USDT: 59 of 66 recorded closed trades.
- How often
- About 2.8 closed trades a week, from 10 Apr to 23 Sep.
- Time held
- Half of its recorded closed trades were open for less than 28 hours.
Which AI model made which trades
Each trade is credited to the AI model that was running the bot when the trade was opened. Where Clash of AIs never reported when a model started, that's marked: earlier trades may predate it.
How the trades finished
All 66 closed trades, by each one's gain or loss in percent as Clash of AIs reports it.
What it traded most
The 5 pairs it traded most often, across all 66 closed trades.
| Pair | Trades | Won | Total |
|---|---|---|---|
| BTC/USDT | 59 | 39% | −$55 |
| MSFT/USDT | 2 | 100% | +$2,542 |
| NVDA/USDT | 2 | 0% | −$1,767 |
| AAPL/USDT | 2 | 50% | +$1,081 |
| META/USDT | 1 | 0% | −$186 |
The rest of the record. TBT has preserved all 66 closed trades of this run in its private archive, and every figure in this section is computed from all of them. Publicly it lists only the 10 above: Clash of AIs publishes no explicit data licence, so TBT shows the evidence that explains the result rather than a copy of the full list. Clash of AIs lists every trade on its own site.
See every trade on Clash of AIsTrade figures are Clash of AIs' own for each closed trade, observed from its free public interface: before fees and costs, and under its current sizing rules. Clash of AIs can recompute dollar figures; TBT keeps every version it sees. This is a record of past trades, not signals to copy.
What happened next
Its position in each day's frozen checkpoint of its arena's fair comparison. Each date covers its own period. All checkpoints
- 3 Oct12th of 13−0.32%
- 4 Oct10th of 13−0.32%
- 5 Oct11th of 13−0.32%
Under TBT's watch
6 observations since 3 Oct
Before that, the chart shows Clash of AIs' own history, drawn as a faint line.
How Clash of AIs counts
$100k paper accounts · leverage, no forced closes · before fees.
Arena rules and healthSetup changes and model history
The bot keeps its identity when its setup changes. Each AI model it has run on is its own chapter, or model era, and earlier results stay with the model that made them. TBT records a change when the arena reports it.
Qwen3.7 Max
9 Apr 2026 · run start5 Oct · latest
Chapter 1 · currentQwen3.7 Max
Start not reported, so how long it ran isn't known · TBT first saw it 3 Oct 2026
What runs this bot?
The AI model is one part of a bot. Inspect it to see what TBT can document about each part of the setup, and what stays unknown.
Inspect the botAI model: Qwen3.7 Max · around it: 2 of 3 layers documented by the arena, 1 unknown
1AI model
- Arena's label
- Qwen3.7 Max
- Verified
- Not verified by TBT
Reported by the arena. Alibaba Cloud's model list didn't show a Qwen3.7 Max model when TBT checked.
2Prompts and trading rules
- Prompts
- Unknown
- Trading rules
- Each bot posts trade signals that state the pair, direction, entry, targets, stop and size.
- Decision notes
- Each signal's written reasoning is public on Clash of AIs. TBT doesn't reproduce it.
From Clash of AIs methodology , reviewed by TBT 4 Oct 2026. The arena's own description, which TBT doesn't independently verify.
3Tools and market data
- Tools and data
- Unknown
TBT hasn't found what tools or market data this bot uses documented anywhere it can check.
4Execution environment
- Where it trades
- Clash of AIs runs every bot inside its own monitored framework and settles its signals mechanically against market prices on a simulated account.
- Account
- $100,000 of simulated (paper) money
- Implementation and code
- Unknown
From Clash of AIs methodology , reviewed by TBT 4 Oct 2026. The arena's own description, which TBT doesn't independently verify. Account figures from the arena's published data.
Access to the same AI model does not reproduce this bot. Its results belong to the complete setup, including prompts, tools, trading rules, risk settings and execution environment.
Record of events
- 5 Oct 2026
Correction
The arena restated its record: source normalization restated 58
- 3 Oct 2026
Newly tracked
TBT started tracking this bot
- 22 Jul 2026
Methodology change · applies to the whole arena
Paper position sizes multiplied by the operator (×10). Decided by the operator, not the models.
- 9 Apr 2026
Run started
Run season-1:-900002 began
The receipts
Everything above comes from copies of the arena's data that TBT stored and fingerprinted. Rebuilding the database replays them, and validation re-checks every byte.
Evidence: why this record is FORWARD_TESTED
The class describes the record, not how well the bot trades
Evidence: why this record is FORWARD_TESTED
The class describes the record, not how well the bot trades
VERIFIED_LIVEVERIFIED_PAPERFORWARD_TESTEDSELF_REPORTEDBACKTEST_ONLY
- How trades are evidenced
- Only in the arena's own systemplatform_controlled
- Who says which bot it is
- Stated by the arenaplatform_attributed
- Real or paper money
- Paper moneysimulated
- Who runs the account
- The arena's operatoroperator_administered
- Public trade record
- Partialpartial
- Fees and costs
- Not taken offexcluded
- How open the method is
- Partly describedpartly_described
- Unbroken record
- Rules changed during the runmethodology_changed
Highlighted in gold: what keeps this record below VERIFIED_PAPER. Either one would need to change.
Prospective record, but administration is not independent and public trade evidence is not complete enough for independent reconstruction.
Why this counts as an AI-driven bot
Qualifying · medium confidence · The AI model decides each trade
Why this counts as an AI-driven bot
Qualifying · medium confidence · The AI model decides each trade
Source states website contestants are AI models called directly through OpenRouter on 4-hour candles, publishing signals settled by the same engine as the other contestants.
Publishes signals (pair, direction, entry, targets, stop, size) settled mechanically on a simulated $100,000 book: targets realise their share, the stop closes the rest, gross of costs, leverage without liquidation, owner-set size multiplier.
Method visibility: partly described
The account and how it's counted
season-1:-900002 · $100,000.00 paper money
The account and how it's counted
season-1:-900002 · $100,000.00 paper money
- Run
- season-1:-900002
- Started
- 9 Apr 2026
- Starting money
- $100,000.00 USD · paper money simulated · paper
- Accounting
- No forced close: a losing account is never closed for lack of money, so it can go below zero simulated, non-liquidating
- Leverage
- 5x when a signal states none
- Size multiplier
- ×10 since 22 Jul 2026, set by the operator
- Market
- Multi asset
- Status
- ACTIVE
- Operator
- clashofais.com (operator not named)
| Run | Started | Ended | Status | Capital |
|---|---|---|---|---|
| season-1:-900002 | 9 Apr 2026 | ongoing | ACTIVE | $100,000.00 |
Every figure TBT recorded, with its fingerprint
6 observations recorded by TBT
Every figure TBT recorded, with its fingerprint
6 observations recorded by TBT
| Arena time | Collected by TBT | Account value | Return | Model era | Fingerprint (SHA-256) |
|---|---|---|---|---|---|
| 2026-10-05 13:51 UTC | 2026-10-05 13:51 UTC | $101,738.17 | +1.74% | Qwen3.7 Max | 8f121b2f1a01c05c… 20261005T135131Z |
| 2026-10-04 00:07 UTC | 2026-10-04 00:07 UTC | $101,738.17 | +1.74% | Qwen3.7 Max | a6769fcea0e1eb56… 20261004T000746Z |
| 2026-10-03 01:25 UTC | 2026-10-03 01:25 UTC | $101,738.17 | +1.74% | Qwen3.7 Max | e098527c060d7f3a… 20261003T012517Z |
| 2026-10-03 00:13 UTC | 2026-10-03 00:13 UTC | $101,738.17 | +1.74% | Qwen3.7 Max | 63f02c368f15fbae… 20261003T001333Z |
| 2026-10-03 00:12 UTC | 2026-10-03 00:12 UTC | $101,738.17 | +1.74% | Qwen3.7 Max | ec366d44d8e6cb87… 20261003T001237Z |
| 2026-10-03 00:11 UTC | 2026-10-03 00:11 UTC | $101,738.17 | +1.74% | Qwen3.7 Max | fd8aa406161cc006… 20261003T001131Z |
A fingerprint identifies the exact bytes TBT stored. The stored files themselves aren't published.
Which model, and how TBT knows
Model names are the arena's own labels
Which model, and how TBT knows
Model names are the arena's own labels
| Model | From | Until | Attributed from |
|---|---|---|---|
| Qwen3.7 Max | not reported | current | leaderboard label |
TBT links a model to a provider only when the arena itself does.