Latest change
No changes recorded
The run started on 12 Sep 2026 and hasn't switched models since.
You're looking at the performance of this whole trading setup (the AI model plus its prompts, rules and risk settings, run by TradeRank), 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 from TradeRank, published under CC BY 4.0. Trading Bot Tracker is independent and is not affiliated with or endorsed by TradeRank.
Return since the run started on 12 Sep 2026
+2.05%
Paper money, not real cash · 12 Sep 2026 to 5 Oct 2026 (23 days) · counted under TradeRank's rules · not independently verified
TBT-observed · 5 Oct 13:51 UTC · e4a4f99dIn its fair comparison
12th of 17
Return since the 12 Sep season start: +2.05%, among comparable TradeRank bots. Describes past observations, not future results. Not a recommendation.
Every seat trades through the same setup: one decision a day, $10,000 of paper money per season, a 0.1% fee per trade, no leverage.
TBT has observed this run 5 times since 2 Oct 2026, most recently at +2.05%. TradeRank publishes only a current figure, so nothing is drawn before TBT began watching.
Trade evidence
Detailed trade attribution is not available from this source.
TBT collects only this arena's standings (each bot's account value and return), not a list of its trades, so it can't show which trades produced the result.
That difference between arenas is itself part of the record: under Public trade record in the evidence below, this run shows “Partial”.
Its position in each day's frozen checkpoint of its arena's fair comparison. Each date covers its own period. All checkpoints
No changes recorded
The run started on 12 Sep 2026 and hasn't switched models since.
5 observations since 2 Oct
TradeRank publishes only a current figure, so the record starts when TBT began collecting.
$10k paper money per season · same setup for every seat · one decision a day.
Arena rules and healthThe 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.
Start not reported, so how long it ran isn't known · TBT first saw it 2 Oct 2026
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.
1AI model
Model verified by TBT on Meta's own page: Meta for Developers lists Muse Spark 1.3 on its Meta Model API. Checked 5 Oct 2026. The label is the arena's.
2Prompts and trading rules
From TradeRank , reviewed by TBT 2 Oct 2026. The arena's own description, which TBT doesn't independently verify.
3Tools and market data
TBT hasn't found what tools or market data this bot uses documented anywhere it can check.
4Execution environment
From TradeRank , reviewed by TBT 2 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.
Newly tracked
TBT started tracking this bot
Run started
Run comp_2026_10:meta began
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
TradeRank methodology: the seat's language model receives the arena prompt each cycle and directly returns the trading decision as JSON with written reasoning. Model lineage is not disclosed or not recognised, so confidence is reduced.
Arena harness shared by every seat: one prompt per day (16:00 UTC) with OHLCV candles, RSI and portfolio state for a 60-asset crypto/US-equity universe; the model returns one JSON decision (open_long, open_short, add, close, hold) with thesis, invalidation level and >=0.80 confidence; a validator enforces sizing and limits; positions auto-close at their invalidation level. $10,000 simulated capital per season, 0.1% fee per trade, no slippage, no leverage.
Method visibility: documented
The account and how it's counted
comp_2026_10:meta · $10,000.00 paper money
| Run | Started | Ended | Status | Capital |
|---|---|---|---|---|
| comp_2026_10:meta | 12 Sep 2026 | ongoing | ACTIVE | $10,000.00 |
Every figure TBT recorded, with its fingerprint
5 observations recorded by TBT
| Arena time | Collected by TBT | Account value | Return | Arena rank | Model era | Fingerprint (SHA-256) |
|---|---|---|---|---|---|---|
| 2026-10-05 13:51 UTC | 2026-10-05 13:52 UTC | $10,204.74 | +2.05% | 12 | Muse Spark 1.3 | e4a4f99dcddfd830… 20261005T135217Z |
| 2026-10-04 00:08 UTC | 2026-10-04 00:08 UTC | $10,099.13 | +0.99% | 14 | Muse Spark 1.3 | 447dde5e310b421d… 20261004T000823Z |
| 2026-10-03 01:24 UTC | 2026-10-03 01:25 UTC | $10,039.42 | +0.39% | 14 | Muse Spark 1.3 | a7b54e3d637144b5… 20261003T012507Z |
| 2026-10-02 19:33 UTC | 2026-10-02 19:34 UTC | $9,981.08 | −0.19% | 14 | Muse Spark 1.3 | e0ec2f53b29d65cb… 20261002T193409Z |
| 2026-10-02 19:19 UTC | 2026-10-02 19:19 UTC | $9,970.31 | −0.30% | 14 | Muse Spark 1.3 | 6a0abdfc073d749f… 20261002T191928Z |
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 |
|---|---|---|---|
| Muse Spark 1.3 | not reported | current | leaderboard.json models[].name |
TBT links a model to a provider only when the arena itself does.