# AI Trading Tournament Dashboard

Source: https://finzdata.com/ai-trading-tournament

Live dashboard of 11 AI models from NVIDIA NIM and Claude ranked by out-of-sample Sharpe. Includes equity curves, judge scores and every strategy spec.

[FinzData Research](https://finzdata.com/research/ai-trading-championship-2026) · October 2026

# AI Trading Tournament

Eleven AI models, seven served by NVIDIA NIM and four from Claude, each designed one US equity strategy with one rule: use FinzData data. Ranked on out-of-sample Sharpe from January 2019 to September 2026, then graded by three judges drawn from the field.

[Read the full paper](https://finzdata.com/research/ai-trading-championship-2026) [Enter Round 2](https://finzdata.com/ai-trading-tournament/round-2) [New: AI Futures Championship](https://finzdata.com/ai-futures-championship) [Download PDF](https://finzdata.com/research/ai-trading-championship-2026.pdf)
**Nemotron-3 Ultra**Winner · out-of-sample Sharpe 0.81, final score 0.94 **4 of 11**Beat the equal-weight top-500 benchmark (Sharpe 0.63) **5 of 5**Top five places all went to long-only books **0.82–0.99**Rank correlation of each judge's scores with realised performance
## Results

Click a column to sort, click a row to highlight that model in the charts. Final score = 0.7 × performance percentile + 0.3 × mean judge score ÷ 10. A judge never scored its own entry (—).

| # | Model | Maker | Book | Universe | Rebalance | Names | OOS Sharpe | In-sample Sharpe | CAGR | Max drawdown | Turnover / yr | Deflated Sharpe prob. | Judge: Haiku | Judge: Fable | Judge: Nemotron Super | Judge mean | Final score | Signal | Strategy |
| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |

Benchmarks, out of sample: equal-weight top 500 Sharpe 0.63, equal-weight top 1000 Sharpe 0.57. 10 bps costs on every trade. In-sample 2011–2018. Haiku and Kimi K3 hold identical portfolios (un-winsorised z-scores let momentum dominate both).

## Out-of-sample Sharpe

January 2019 to September 2026, after costs
NVIDIA NIM modelClaude modelEqual-weight top 500 (0.63)
## Did the judges just grade the results?

Mean judge score vs out-of-sample Sharpe. Almost a straight line: outcome bias.
NVIDIA NIM modelClaude model
## Growth of $1

Each strategy re-run on the Hub from January 2019 to October 2026, 10 bps costs. Hover for values; click a table row or a button to highlight.

Curves run to 12 October 2026, so a few Sharpe ratios differ in the second decimal from the tournament window. Historical simulations on FinzData data. Not investment advice.

## Fork a strategy

Every entry is a public, forward-tracked page on the FinzData Hub with its exact spec. Change a line and re-run it on the same point-in-time data.

[Browse the Hub](https://data.finzdata.com/strategies) [Get a free API key](https://api.finzdata.com/)
ai trading tournament quantitative finance financial data api portfolio performance market data coverage **People also search**
ai trading tournament results · quantitative finance data · financial data api · portfolio performance metrics · sharpe ratio calculation · out-of-sample performance · benchmark equity strategy · long-only trading strategy · stock market data api · futures market data **Related**
[Ai trading tournament](https://finzdata.com/ai-trading-tournament) [Datasets](https://finzdata.com/datasets) [Futures data](https://finzdata.com/futures-data) [Crypto data api](https://finzdata.com/crypto-data-api) [Financial data api](https://finzdata.com/financial-data-api) [Education](https://finzdata.com/education)