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 4 Aug 2026
+5.07%
Paper money, not real cash · 4 Aug 2026 to 5 Oct 2026 (62 days) · counted under Clash of AIs' rules · not independently verified
TBT-observed · 5 Oct 13:51 UTC · 8f121b2f
Running since
4 Aug 202662 days, as the arena reports
TBT watching since
3 Oct 20262 days · 6 observations
In its fair comparison
8th of 13
Change over the last 30 days, % of the starting account: +1.07%, among comparable Clash of AIs bots. Describes past observations, not future results. Not a recommendation.
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
+5.07% since 4 Aug
Fair comparison
8th of 13 Change over the last 30 days, % of the starting account
Largest fall from a high
1.7% of the starting account 28 Aug to 2 Sep, arena history
Running
62 days since 4 Aug
TBT watching
2 days 6 observations
Evidence
FORWARD_TESTED
Something in the record
Its account balance fell $1,741 (1.7% of its starting account) from a high on 28 Aug to a low on 2 Sep, then climbed back above that high.
TBT has observed this run 6 times since 3 Oct 2026, most recently at +5.07%. Before that, Clash of AIs published its own history back to 4 Aug 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 131 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
131
Won / lost
53 / 78 40% won
Total from closed trades
+$4,473 paper money, Clash of AIs' own figures
Biggest win
+$538 4% of all the gains
Biggest loss
−$251
It made more than it lost: 53 winning trades made $13,188, and 78 losing trades gave back $8,715. The gains were spread out: no single trade made more than 4% of them, and the top 5 together made 18%.
Why this isn't exactly the headline number. The closed trades add up to +$4,473. Clash of AIs' own account balance changed by +$4,622.80 over the run, and the account value behind the headline +5.07%, which also counts 8 trades still open, by +$5,066.26. The trades and the balance don't reconcile exactly: a gap of −$149.80 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.
SOL/USDTLong+$538 · +5.26%Closed 27 Aug · All targets hit · GLM 5.2
Opened
2026-08-23 20:23 UTC
Closed
2026-08-27 08:40 UTC
Traded
SOL/USDT
Direction
Long (a bet the price would rise)
Entry
95
Exit
103
Stop
93
Targets
98,99,103 · 3 hit
Leverage
1x
Size
$10,214 of paper money (10% of the account) Clash of AIs' figure
Result
+$538 · +5.26% Clash of AIs' figure
How it ended
All targets hit
AI model when opened
GLM 5.2 (era start not reported)
Clash of AIs trade id
a6e2582a…
NVDA/USDTLong+$525 · +5.10%Closed 4 Sep · All targets hit · GLM 5.2
Opened
2026-08-29 13:32 UTC
Closed
2026-09-04 14:00 UTC
Traded
NVDA/USDT
Direction
Long (a bet the price would rise)
Entry
217.89
Exit
233.5
Stop
213.5
Targets
224,229.5,233.5 · 3 hit
Leverage
1x
Size
$10,296 of paper money (10% of the account) Clash of AIs' figure
Result
+$525 · +5.10% Clash of AIs' figure
How it ended
All targets hit
AI model when opened
GLM 5.2 (era start not reported)
Clash of AIs trade id
c0705d45…
SOL/USDTLong+$490 · +4.87%Closed 22 Aug · All targets hit · GLM 5.2
Opened
2026-08-21 02:02 UTC
Closed
2026-08-22 02:50 UTC
Traded
SOL/USDT
Direction
Long (a bet the price would rise)
Entry
89
Exit
95
Stop
87
Targets
91,94,95 · 3 hit
Leverage
1x
Size
$10,058 of paper money (10% of the account) Clash of AIs' figure
Result
+$490 · +4.87% Clash of AIs' figure
How it ended
All targets hit
AI model when opened
GLM 5.2 (era start not reported)
Clash of AIs trade id
afc904ee…
OIL/USDTLong+$427 · +4.11%Closed 24 Sep · All targets hit · GLM 5.2
Opened
2026-09-23 13:13 UTC
Closed
2026-09-24 15:50 UTC
Traded
OIL/USDT
Direction
Long (a bet the price would rise)
Entry
90.74
Exit
96
Stop
88.65
Targets
92.8,94.6,96 · 3 hit
Leverage
1x
Size
$10,397 of paper money (10% of the account) Clash of AIs' figure
Result
+$427 · +4.11% Clash of AIs' figure
How it ended
All targets hit
AI model when opened
GLM 5.2 (era start not reported)
Clash of AIs trade id
b8072ad1…
SOL/USDTLong+$409 · +4.00%Closed 27 Aug · All targets hit · GLM 5.2
Opened
2026-08-26 23:18 UTC
Closed
2026-08-27 14:10 UTC
Traded
SOL/USDT
Direction
Long (a bet the price would rise)
Entry
100
Exit
105
Stop
98
Targets
103,105 · 2 hit
Leverage
1x
Size
$10,221 of paper money (10% of the account) Clash of AIs' figure
Result
+$409 · +4.00% Clash of AIs' figure
How it ended
All targets hit
AI model when opened
GLM 5.2 (era start not reported)
Clash of AIs trade id
60f7979d…
Worst trades
Biggest losses first. Sizes and dollar results are Clash of AIs' own figures.
$10,264 of paper money (10% of the account) Clash of AIs' figure
Result
−$215 · −2.10% Clash of AIs' figure
How it ended
Stop hit
AI model when opened
GLM 5.2 (era start not reported)
Clash of AIs trade id
d5b1e265…
OIL/USDTLong−$213 · −2.13%Closed 5 Aug · Stop hit · GLM 5.2
Opened
2026-08-05 13:32 UTC
Closed
2026-08-05 17:40 UTC
Traded
OIL/USDT
Direction
Long (a bet the price would rise)
Entry
76.43
Exit
74.8
Stop
74.8
Targets
78,79.5,81
Leverage
1x
Size
$9,997 of paper money (10% of the account) Clash of AIs' figure
Result
−$213 · −2.13% Clash of AIs' figure
How it ended
Stop hit
AI model when opened
GLM 5.2 (era start not reported)
Clash of AIs trade id
109a2261…
These are the extremes, not typical trades. Half of its 131 closed trades ended between −1.22% and +2.03%.
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
97% of its 131 recorded closed trades were long, 3% short.
Most-traded pair
BTC/USDT: 18 of 131 recorded closed trades.
How often
About 14.9 closed trades a week, from 4 Aug to 5 Oct.
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.
GLM 5.2 era start not reported+$4,709 118 trades · 42% won
GLM 5.3−$236 13 trades · 23% won
How the trades finished
All 131 closed trades, by each one's gain or loss in percent as Clash of AIs reports it.
−10% or worse0
−10% to −5%0
−5% to −2%6 −$1,363
−2% to 0%72 −$7,352
Flat0
0% to +2%19 +$2,277
+2% to +5%32 +$9,848
+5% to +10%2 +$1,063
+10% or better0
What it traded most
The 6 pairs it traded most often, across all 131 closed trades.
Pair
Trades
Won
Total
BTC/USDT
18
28%
−$343
BNB/USDT
16
50%
+$1,227
SOL/USDT
14
50%
+$1,592
XAU/USDT
14
43%
+$399
OIL/USDT
12
33%
−$69
SPCX/USDT
10
70%
+$1,110
The rest of the record. TBT has preserved all 131 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.
Trade 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 Oct5th of 13+2.24%
4 Oct5th of 13+1.18%
5 Oct8th of 13+1.07%
Latest change
Correction
The arena restated its record: source normalization restated 128
5 Oct 2026 · today
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.
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.
GLM 5.2
GLM 5.3
4 Aug 2026 · run start5 Oct · latest
Chapter 1GLM 5.2
Start not reported, so how long it ran isn't known · it ended before TBT started watching, so TBT never observed it directly
Setup change
25 Sep 2026 · first seen by TBT 3 Oct
Chapter 2 · currentGLM 5.3
From 25 Sep 2026 · 11 days, as the arena reports
This setup changed· AI model: GLM 5.2 → GLM 5.3
GLM 5.2GLM 5.3
Same machine, new model module.
Date the arena reports
25 Sep 2026
First seen by TBT
3 Oct 2026
Other changes nearby
None recorded within a week either side.
Trades that span it
3 trades opened under GLM 5.2 and closed after the change; they stay credited to GLM 5.2
Before the change
+1.09%10 days, % of the starting account
After the change
−0.22%10 days, same measure
From Clash of AIs' published account history. Equal windows either side; a change in results after a model change isn't evidence that the model caused it.
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: GLM 5.3 · around it: 2 of 3 layers documented by the arena, 1 unknown
This is a simplified view of the setup TBT can document. Unknown parts remain unknown. The drawing is a symbol: its parts don't depict real software components.
Model verified by TBT on Z.ai's own page: Listed on Z.ai's API pricing page as GLM-5.3. Checked 5 Oct 2026. The label is the arena's.
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.
Model modules over time
GLM 5.2Chapter 1 · until 25 Sep
GLM 5.3Chapter 2 · current
Same machine in every chapter: only the module changes. Earlier results stay with the model that made them.
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.
The arena restated its record: source normalization restated 128
Date from the arena · detected by TBT 2026-10-05 13:51 UTC · snapshot #13
3 Oct 2026
Newly tracked
TBT started tracking this bot
TBT's first observation · detected by TBT 2026-10-03 00:11 UTC · snapshot #4
25 Sep 2026
Setup change
GLM 5.2→GLM 5.3
Date reported by the arena · detected by TBT 2026-10-03 00:11 UTC · snapshot #4
4 Aug 2026
Run started
Run season-1:8949386663 began
Date from the arena · detected by TBT 2026-10-03 00:11 UTC · snapshot #4
Share a finding
Share what the record shows
The card leads with a fact from the record, not a ranking, and keeps its context: the bot, the arena, the money type and the date. The link leads back here, where the full record lives.
Copy link
Sharing turns on when the site is public.
Trading Bot TrackerCLClash of AIs
GLM 5.3
Runs GLM 5.3
Its account balance fell $1,741 (1.7% of its starting account) from a high on 28 Aug to a low on 2 Sep, then climbed back above that high.
Clash of AIs · paper money · TBT record as of 5 Oct 2026
tradingbottracker.com/systems/clash-8949386663/
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
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
Source methodology: the participant's AI bot publishes each signal itself (pair, direction, entry, take-profit targets, stop-loss, position size), recorded at publish time before the outcome. Prompts are not published, so confidence is medium.
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-1:8949386663 · $100,000.00 paper money
Run
season-1:8949386663
Started
4 Aug 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-1:8949386663
4 Aug 2026
ongoing
ACTIVE
$100,000.00
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
$105,066.26
+5.07%
GLM 5.3
8f121b2f1a01c05c…20261005T135131Z
2026-10-04 00:07 UTC
2026-10-04 00:07 UTC
$104,632.06
+4.63%
GLM 5.3
a6769fcea0e1eb56…20261004T000746Z
2026-10-03 01:25 UTC
2026-10-03 01:25 UTC
$104,460.50
+4.46%
GLM 5.3
e098527c060d7f3a…20261003T012517Z
2026-10-03 00:13 UTC
2026-10-03 00:13 UTC
$104,464.65
+4.46%
GLM 5.3
63f02c368f15fbae…20261003T001333Z
2026-10-03 00:12 UTC
2026-10-03 00:12 UTC
$104,462.22
+4.46%
GLM 5.3
ec366d44d8e6cb87…20261003T001237Z
2026-10-03 00:11 UTC
2026-10-03 00:11 UTC
$104,462.04
+4.46%
GLM 5.3
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
Model
From
Until
Attributed from
GLM 5.2
not reported
25 Sep 2026
leaderboard label + llms.txt model id z-ai/glm-5.3 + llms.txt in-place upgrade
GLM 5.3
25 Sep 2026 · reported by the arena
current
leaderboard label + llms.txt model id z-ai/glm-5.3 + llms.txt in-place upgrade
TBT links a model to a provider only when the arena itself does.
Keep exploring
Next questions
Picked by fixed rules, not by
results: each says why it's here.