Stress-test your TradingView strategy on unseen years, before trusting it.
Upload the “List of trades” export of your TradingView strategy: free preview first, then the full dossier. Or paste your Pine script and the free judge replays it on a period kept out of the search.
Three steps, the first two free.
Your export or your script
In the TradingView Strategy Tester, the “List of trades” tab exports your trades in two clicks, for any market. Or paste the Pine script of your strategy.
The free preview
The judge replays your script on a period kept out of the search. For an export, the preview shows what your trades give before and after your cut date, fees included. No account.
The full dossier, €9
For a “List of trades” export: Monte Carlo stress test, drawdown against holding the asset, stability year by year, and one improvement lead to test, with a prompt ready for your AI.
A judge that also publishes what disappoints.
Famous theories, judged on unseen years
In the Pantheon, 36 proofs pitted ten famous rules against plain buy-and-hold: 0 “survives”, and 20 of 36 have a smaller maximum drawdown. Taleb’s 90/10 barbell divides the drawdown by 10 over 30 sealed years (5.0% vs 50.3%).
See the theorists’ verdict →The Lab’s Pine export, checked in TradingView
6 of the 6 leaderboard strategies, 234 of 234 trades, give the same trades one by one in the real TradingView, quantities included (Lab 236 export, test of 8 October 2026).
This parity concerns the Lab, which runs the rule itself. The dossier does not replay your rule: it reads the trades of your export.
How the comparison works →No “survives” on pure noise
Measured before release (11 October 2026): on markets of pure noise, the judge said “survives” in none of 350 research sessions, even when the search believed it was improving.
Read the method →Same judge for your strategy: dossier on your export · free judge · the noise measurement
Check for free. Dossier €9. Go deeper in the Lab.
- The online judge, no account
- The dossier preview on your export
- The Lab on your computer
- Once, or 1 purchased credit
- On the “List of trades” export, every market
- Free preview first, no account
- Packs: €9 (1), €25 (5), €49 (10)
- 1 credit = 1 audit dossier or 1 Lab certificate
- One-time payment, credits never expire
All pricing · No “List of trades” export in your TradingView plan? Paste your Pine script into the online judge: a free verdict, no account.
Research on past data, never advice. Paying never changes a verdict. Past results do not predict future results.
Who is behind it: made in Montpellier, France, by Chris · TENDIL COURTAGE, sole trader (entrepreneur individuel), RCS Montpellier 442 135 091 · a question? Direct answer by email: [email protected] · about me
The free Lab, driven by your AI.
A free app for Windows and Linux: search as much as you want on your own computer, even offline. Your AI (Claude, ChatGPT, DeepSeek…) can drive it, and the verdict stays with the same judge: a sealed period, every attempt counted.
Common questions
What is strategyarena.io (Strategy Arena)?
Strategy Arena (strategyarena.io, published by Tendil Courtage, Montpellier) is an independent, educational test bench for trading strategies. It is not related to strategie-arena.com. A free online judge tests a Pine script in your browser on a sealed period. A €9 audit dossier reads the “List of trades” export of your TradingView strategy, after a free preview. The free Strategy Arena Lab app (Windows and Linux) goes further, AI agents included (over MCP). Research on past data, never advice.
Is Strategy Arena Lab free?
Yes. The app, the MCP connection, backtests, sweeps, Pine export and the sealed proof are free. Paid options (audit dossier, credits) are on the pricing page. Paying never changes a verdict.
Does the Lab place live orders?
No. It is a research and backtesting tool on past data. It places no broker orders and gives no investment advice.
What is the public arena?
A secondary part of the site: 75 paper strategies run in simulation with virtual capital, losses included. It does not replace a test of your own idea in the Lab.