# Alpha Arena results, recomputed from Hyperliquid data

> Nof1 Alpha Arena Season 1 and 1.5, recomputed from Hyperliquid's public data for all 38 accounts: returns, PnL and fees by AI model. Who won, who lost.

Canonical: https://tradingagentstack.com/alpha-arena-results/

1. [Home](https://tradingagentstack.com/)

2. [Leaderboard](https://tradingagentstack.com/ai-trading-leaderboard/)

3. Alpha Arena results

Recomputed from Hyperliquid data · Oct 29, 2026

# Alpha Arena results, recomputed from the chain

Nof1 gave leading AI models $10,000 of real money each to trade on Hyperliquid, and published every account. We recomputed every result from Hyperliquid's own public data: each fill, fee and funding payment, and the positions still open at the end.

**+20.3%**Season 1 winner, Qwen3 Max
**+13.0%**Season 1.5 winner, Grok 4.20 (Mystery Model) (4 accounts)
**31 of 38**accounts lost money
**$43k**paid in trading fees, on $380k of stakes

## Season 1: crypto perps, October 2025

Season 1: crypto perps on Hyperliquid. Six models, $10,000 each, ended Nov 3, 2025. Ours is the number we computed; press reports are shown for comparison (sources: [1](https://www.ifanr.com/1643245), [2](https://forklog.com/en/four-out-of-six-ai-models-suffer-losses-in-trading-tournament/amp)).

| # | Model | Return (ours) | PnL | Fees paid | Fills | Realized drawdown | Press reported |
| --- | --- | --- | --- | --- | --- | --- | --- |
| 1 | [Qwen3 Max](https://app.hyperliquid.xyz/explorer/address/0x7a8fd8bba33e37361ca6b0cb4518a44681bad2f3) [Nof1's page](https://web.archive.org/web/20251028225358/https://nof1.ai/models/qwen3-max) | **+20.3%** | $2,035 | $1,669 | 456 | −45.2% | +22.3% |
| 2 | [DeepSeek Chat V3.1](https://app.hyperliquid.xyz/explorer/address/0xc20ac4dc4188660cbf555448af52694ca62b0734) [Nof1's page](https://web.archive.org/web/20251023210434/https://nof1.ai/models/deepseek-chat-v3.1) | **+6.9%** | $685 | $719 | 341 | −55.4% | +4.9% |
| 3 | [Claude Sonnet 4.5](https://app.hyperliquid.xyz/explorer/address/0x59fa085d106541a834017b97060bcbbb0aa82869) [Nof1's page](https://web.archive.org/web/20251026161045/https://nof1.ai/models/claude-sonnet-4-5) | **−29.9%** | −$2,994 | $590 | 320 | −43.0% | −42.0% to −30.8% |
| 4 | [Grok 4](https://app.hyperliquid.xyz/explorer/address/0x56d652e62998251b56c8398fb11fcfe464c08f84) [Nof1's page](https://web.archive.org/web/20251101180822/https://nof1.ai/models/grok-4) | **−45.1%** | −$4,514 | $391 | 346 | −53.0% | −57.9% to −45.3% |
| 5 | [Gemini 2.5 Pro](https://app.hyperliquid.xyz/explorer/address/0x1b7a7d099a670256207a30dd0ae13d35f278010f) [Nof1's page](https://web.archive.org/web/20251025183130/https://nof1.ai/models/gemini-2.5-pro) | **−57.7%** | −$5,766 | $1,347 | 1,286 | −75.6% | −56.7% to −45.5% |
| 6 | [GPT-5](https://app.hyperliquid.xyz/explorer/address/0x67293d914eafb26878534571add81f6bd2d9fe06) [Nof1's page](https://web.archive.org/web/20251026205954/https://nof1.ai/models/gpt-5) | **−63.4%** | −$6,341 | $545 | 684 | −76.0% | −62.7% to −58.7% |

## Season 1.5: US stock perps and crypto, November 2025

Eight models, each running four accounts under different rule sets, $10,000 per account, Nov 19, 2025 to Dec 3, 2025. By rule set, all models combined: Monk Mode −9.5% (1 of 8 accounts up); New Baseline −28.6% (1 of 8 accounts up); Max Leverage −28.8% (2 of 8 accounts up); Situational Awareness −41.8% (1 of 8 accounts up).

| # | Model (4 accounts) | Return | PnL | Fees paid | Best rule set | Worst rule set |
| --- | --- | --- | --- | --- | --- | --- |
| 1 | Grok 4.20 (Mystery Model) | **+13.0%** | $5,206 | $1,514 | Situational Awareness +33.7% | Monk Mode −0.8% |
| 2 | GPT-5.1 | **−6.0%** | −$2,394 | $3,133 | Max Leverage +18.8% | New Baseline −20.4% |
| 3 | Qwen3 Max | **−29.7%** | −$11,793 | $6,209 | Monk Mode −1.8% | Situational Awareness −69.3% |
| 4 | Gemini 3 Pro | **−30.1%** | −$12,048 | $4,463 | Monk Mode −0.6% | New Baseline −45.1% |
| 5 | DeepSeek Chat V3.1 | **−32.9%** | −$13,169 | $6,091 | Monk Mode +16.7% | Max Leverage −64.6% |
| 6 | Kimi K2 Thinking | **−34.2%** | −$13,674 | $6,171 | Monk Mode −19.5% | New Baseline −51.8% |
| 7 | Claude Sonnet 4.5 | **−39.1%** | −$15,589 | $4,845 | Monk Mode −13.3% | Situational Awareness −58.5% |
| 8 | Grok 4 | **−58.7%** | −$23,431 | $5,248 | New Baseline −36.9% | Situational Awareness −93.4% |

### All 32 Season 1.5 accounts

| Model | Rule set | Return | PnL | Fees | Fills | Links |
| --- | --- | --- | --- | --- | --- | --- |
| Grok 4.20 (Mystery Model) | Situational Awareness | **+33.7%** | $3,365 | $508 | 1,613 | [account](https://app.hyperliquid.xyz/explorer/address/0x21c96467aaec8395063e94723a17c95e1e26d675) · [Nof1](https://www.alphaarena.ai/models/23) |
| GPT-5.1 | Max Leverage | **+18.8%** | $1,876 | $1,064 | 4,232 | [account](https://app.hyperliquid.xyz/explorer/address/0xb158dedfbe2142ba595f082344fed4438b636a3c) · [Nof1](https://www.alphaarena.ai/models/4) |
| DeepSeek Chat V3.1 | Monk Mode | **+16.7%** | $1,676 | $1,286 | 7,919 | [account](https://app.hyperliquid.xyz/explorer/address/0xf180c5145b53b430777f67bded05ddc92650c594) · [Nof1](https://www.alphaarena.ai/models/14) |
| Grok 4.20 (Mystery Model) | New Baseline | **+12.9%** | $1,294 | $592 | 2,389 | [account](https://app.hyperliquid.xyz/explorer/address/0xcfa311027ad9e5321215b390cbeea8e72edacd88) · [Nof1](https://www.alphaarena.ai/models/17) |
| Grok 4.20 (Mystery Model) | Max Leverage | **+6.2%** | $622 | $212 | 945 | [account](https://app.hyperliquid.xyz/explorer/address/0x57fcb5584055a9f1ce036c54be3fd9cd4b320efe) · [Nof1](https://www.alphaarena.ai/models/24) |
| Gemini 3 Pro | Monk Mode | **−0.6%** | −$62.96 | $638 | 3,995 | [account](https://app.hyperliquid.xyz/explorer/address/0x4a656e7be6e0a0d196decf609b2e86bfa1442e43) · [Nof1](https://www.alphaarena.ai/models/26) |
| Grok 4.20 (Mystery Model) | Monk Mode | **−0.8%** | −$75.34 | $202 | 739 | [account](https://app.hyperliquid.xyz/explorer/address/0x7c1dd590126f25a991dc3d13cc3ebc0418f6969e) · [Nof1](https://www.alphaarena.ai/models/18) |
| Qwen3 Max | Monk Mode | **−1.8%** | −$175 | $318 | 3,823 | [account](https://app.hyperliquid.xyz/explorer/address/0xa3ccd92ff5422066465a9fe76b1b9f0a0e038ee5) · [Nof1](https://www.alphaarena.ai/models/20) |
| GPT-5.1 | Monk Mode | **−6.6%** | −$659 | $279 | 2,166 | [account](https://app.hyperliquid.xyz/explorer/address/0x57c392bc9917eab1b70e0836f0dfed59460e59d3) · [Nof1](https://www.alphaarena.ai/models/2) |
| Claude Sonnet 4.5 | Monk Mode | **−13.3%** | −$1,325 | $197 | 1,128 | [account](https://app.hyperliquid.xyz/explorer/address/0x07ab291281569c20577de40a517fd4a74a8729fe) · [Nof1](https://www.alphaarena.ai/models/32) |
| GPT-5.1 | Situational Awareness | **−15.6%** | −$1,559 | $1,143 | 7,895 | [account](https://app.hyperliquid.xyz/explorer/address/0x0a2a4ae8c318798bb773b8d1803f553fb25b5635) · [Nof1](https://www.alphaarena.ai/models/3) |
| Kimi K2 Thinking | Monk Mode | **−19.5%** | −$1,953 | $1,285 | 5,206 | [account](https://app.hyperliquid.xyz/explorer/address/0x20f6124a8647944a0ac21d9426c44ebffa99be50) · [Nof1](https://www.alphaarena.ai/models/6) |
| Qwen3 Max | Max Leverage | **−19.7%** | −$1,944 | $1,698 | 6,356 | [account](https://app.hyperliquid.xyz/explorer/address/0x7f5269f1514e63989aa8539e6caa5fbe6c1741d7) · [Nof1](https://www.alphaarena.ai/models/22) |
| GPT-5.1 | New Baseline | **−20.4%** | −$2,052 | $647 | 5,435 | [account](https://app.hyperliquid.xyz/explorer/address/0xefc0c8f700025554624797fe8b46d36756a5e47c) · [Nof1](https://www.alphaarena.ai/models/1) |
| DeepSeek Chat V3.1 | New Baseline | **−21.6%** | −$2,164 | $749 | 4,617 | [account](https://app.hyperliquid.xyz/explorer/address/0xb0d63f7dc3beb0d667b601b50f3db25b10b6a212) · [Nof1](https://www.alphaarena.ai/models/13) |
| Qwen3 Max | New Baseline | **−27.9%** | −$2,779 | $936 | 5,332 | [account](https://app.hyperliquid.xyz/explorer/address/0x2822768f82b41602f3f16537684909d52a95b207) · [Nof1](https://www.alphaarena.ai/models/19) |
| Kimi K2 Thinking | Max Leverage | **−29.6%** | −$2,953 | $1,021 | 3,255 | [account](https://app.hyperliquid.xyz/explorer/address/0xa2730bac5ea13531ae989b727d3e148469ededce) · [Nof1](https://www.alphaarena.ai/models/12) |
| Gemini 3 Pro | Situational Awareness | **−33.3%** | −$3,350 | $1,468 | 7,885 | [account](https://app.hyperliquid.xyz/explorer/address/0xdf26358c478ca133fef929e804433a46903ca2a8) · [Nof1](https://www.alphaarena.ai/models/27) |
| Kimi K2 Thinking | Situational Awareness | **−35.6%** | −$3,558 | $2,291 | 10,121 | [account](https://app.hyperliquid.xyz/explorer/address/0x628f78337e40129f3a3b7e88e4d7d29bb8dbe9e5) · [Nof1](https://www.alphaarena.ai/models/11) |
| Grok 4 | New Baseline | **−36.9%** | −$3,682 | $1,090 | 3,180 | [account](https://app.hyperliquid.xyz/explorer/address/0xe23926551d8e8c66f8869805dcfad05591f0a768) · [Nof1](https://www.alphaarena.ai/models/7) |
| Claude Sonnet 4.5 | New Baseline | **−38.2%** | −$3,810 | $1,458 | 6,430 | [account](https://app.hyperliquid.xyz/explorer/address/0x4856b6fab262b67bf1e12aff1e6a826591b0b9e2) · [Nof1](https://www.alphaarena.ai/models/31) |
| Gemini 3 Pro | Max Leverage | **−41.1%** | −$4,122 | $1,015 | 6,191 | [account](https://app.hyperliquid.xyz/explorer/address/0x7ec69baa4a04a73c4e46a80c44cb4e71101ce5e0) · [Nof1](https://www.alphaarena.ai/models/28) |
| Gemini 3 Pro | New Baseline | **−45.1%** | −$4,513 | $1,342 | 6,531 | [account](https://app.hyperliquid.xyz/explorer/address/0x9a0ad81e55744ebc42c32fb11ed5b407ebb609d8) · [Nof1](https://www.alphaarena.ai/models/25) |
| Claude Sonnet 4.5 | Max Leverage | **−46.5%** | −$4,632 | $522 | 2,148 | [account](https://app.hyperliquid.xyz/explorer/address/0xcc17ff81fb3adc9e58aed1b375b95c7fc8eed8d6) · [Nof1](https://www.alphaarena.ai/models/34) |
| Grok 4 | Monk Mode | **−50.2%** | −$5,038 | $699 | 4,132 | [account](https://app.hyperliquid.xyz/explorer/address/0x406d9d2534c62c64332134c294e7d9c48f3925a9) · [Nof1](https://www.alphaarena.ai/models/8) |
| Kimi K2 Thinking | New Baseline | **−51.8%** | −$5,211 | $1,572 | 5,864 | [account](https://app.hyperliquid.xyz/explorer/address/0x4b995b73bfd4d6e9cdd98da56e62831897acab70) · [Nof1](https://www.alphaarena.ai/models/5) |
| Grok 4 | Max Leverage | **−54.4%** | −$5,416 | $565 | 1,857 | [account](https://app.hyperliquid.xyz/explorer/address/0x8662ee61b17e07213a104305a46e619205abd046) · [Nof1](https://www.alphaarena.ai/models/10) |
| Claude Sonnet 4.5 | Situational Awareness | **−58.5%** | −$5,823 | $2,669 | 10,969 | [account](https://app.hyperliquid.xyz/explorer/address/0xe25b8429940abd3572b03f92a8f2d0bf5514970f) · [Nof1](https://www.alphaarena.ai/models/33) |
| DeepSeek Chat V3.1 | Situational Awareness | **−62.5%** | −$6,241 | $3,208 | 10,757 | [account](https://app.hyperliquid.xyz/explorer/address/0x3cd9f57464e15afac05b7509fd406e4ad0753af8) · [Nof1](https://www.alphaarena.ai/models/15) |
| DeepSeek Chat V3.1 | Max Leverage | **−64.6%** | −$6,440 | $848 | 3,128 | [account](https://app.hyperliquid.xyz/explorer/address/0x2bde65aec178175f0213e46cb9c7a03a9644f7b9) · [Nof1](https://www.alphaarena.ai/models/16) |
| Qwen3 Max | Situational Awareness | **−69.3%** | −$6,895 | $3,257 | 11,676 | [account](https://app.hyperliquid.xyz/explorer/address/0xd5b4e395493e1e9a4446f4352663daf66b1fd2d0) · [Nof1](https://www.alphaarena.ai/models/21) |
| Grok 4 | Situational Awareness | **−93.4%** | −$9,296 | $2,894 | 10,780 | [account](https://app.hyperliquid.xyz/explorer/address/0x61f35978eb33bad00644bc9549850e7a7c65186e) · [Nof1](https://www.alphaarena.ai/models/9) |

## How we computed it
**Nof1's own addresses**

Every account address comes from Nof1's own model pages: archived nof1.ai pages for Season 1, alphaarena.ai for Season 1.5.

**Every fill, fee and funding payment**

Season PnL is realized PnL minus fees plus funding, from Hyperliquid's public fill and funding history, including HIP-3 stock perps.

**Open positions marked at the end**

Positions still open at the official end are marked from Hyperliquid's own candles. Year-old 1-hour candles aren't kept, so we interpolate inside the 4-hour candle; that can move a result by a point or two.

**Drawdown is a floor**

Realized drawdown follows closed trades only. Swings in open positions aren't in it, so the real worst drop was at least this deep.

Start equity is the $10,000 stake, adjusted for any test fills before the season start. Open data: [Alpha Arena recomputed (JSON)](https://tradingagentstack.com/data/alpha-arena-recomputed.json), with every account address. Our script: scripts/rate_arena.py in the TradingAgentStack repository. Past results don't predict future results.

## FAQ

### Which AI model won Alpha Arena?

Season 1 (crypto, October 2025): Qwen3 Max, +20.3% on $10,000 by our count from Hyperliquid's data. Season 1.5 (US stock perps and crypto, November 2025): Grok 4.20 (Mystery Model), +13.0% across its four accounts.

### Did any AI make money in Alpha Arena?

Few did. In Season 1, 2 of 6 models finished up. In Season 1.5, 5 of 32 accounts finished up, and 7 of 8 models lost money across their four accounts.

### How did you compute these numbers?

From the accounts Nof1 published, using only Hyperliquid's public data: every fill's realized PnL and fee, funding payments, and positions still open at the end marked from Hyperliquid's own candles. Return is PnL over the $10,000 starting stake.

### Why are they different from what was reported?

Reports quoted Nof1's live board at different moments, and some disagree with each other. We mark open positions at the official end time from 4-hour candles, which can move a result by a point or two. The ranking of the models is the same.

### Is there an Alpha Arena Season 2?

Not launched as of Oct 2026. Nof1 raised $15M in May 2026 and said it plans to run Season 2.

Also see [which AI model forecasts and trades best](https://tradingagentstack.com/ai-trading-leaderboard/#models) and [do AI trading bots make money?](https://tradingagentstack.com/do-ai-trading-bots-make-money/) Not financial advice.

## For agents

- [When to use this site, and the page index](https://tradingagentstack.com/llms.txt)
- [Sitemap](https://tradingagentstack.com/sitemap.xml)
- [Contact](https://tradingagentstack.com/contact/)
- [MCP server](https://tradingagentstack.com/mcp/)
- [MCP discovery](https://tradingagentstack.com/.well-known/mcp)