Codex 5.5 vs Claude Code Hyperliquid Trading Challenge
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Unlock all features
FREE: Get instant access to 10 AI summaries, chats, or transcripts per day.
Related videos
Claude Code vs Codex vs Cursor (an honest comparison)
Theo - t3․gg
17.9k views
OpenAI Misses Targets, Codex vs Claude, Elon vs Sam Trial, Big Hyperscaler Beats, Peptide Craze
All-In Podcast
67.6k views
Costco vs. Sam's Club Cooking Challenge
Mythical Kitchen
217.0k views
Cursor, Claude Code and Codex all have a BIG problem
Theo - t3․gg
134.9k views
Dollar Tree vs. Aldi Budget Cooking Challenge
Mythical Kitchen
195.1k views
Claude Code is about to break everything
Wes Roth
51.1k views
Bitcoin CME Gap at $110K! Plus ASTRA vs Hyperliquid DEX War
Coin Bureau
36.0k views
Hyperliquid’s USDH Launch Is COMING: Absolute Gamechanger!
Coin Bureau
26.2k views
Husband Vs. Wife Cooking Challenge
Mythical Kitchen
301.7k views
Dollar Tree vs. Sam's Club Cooking Challenge
Mythical Kitchen
400.4k views
Top Comments (10)
The interesting comparison is consistency across runs rather than any single result, since variance is the part that decides whether an agent is actually deployable.
my codex does not agee to trade on its own, how did you do that?
Can you add gemini 3.5 flash it scored the highest on the financial benchmark so i wonder how it will do.
Nice one!
can you do one using a platform also usable by US residents?
My biggest issue with this test is that if the two models aren’t running at the same time, they’re not really trading the same market. Same prompt isn’t enough when volatility, liquidity and trend can change minute by minute. A fairer comparison would run both agents in parallel under identical constraints, ideally across multiple runs.
You didn’t show the strategy codex decided to use I don’t know if that was purposely or on accident
Can you do Forex EUR/USD it's very good for that and it's volatile so good opportunities
Brother , try Qwen 3.7 I think the framework is better on an hourly basis
Now we need to see how it goes with Opus 4.8 :D
Unlock the Data Inside
Turn Videos into Knowledge
- Get FREE 10/day: transcripts, summaries, chats
- Chat with videos, export text & PDF
- $1 free API credit for RAG, chatbots & research
Free forever plan • All features unlocked
Top Comments (10)
The interesting comparison is consistency across runs rather than any single result, since variance is the part that decides whether an agent is actually deployable.
my codex does not agee to trade on its own, how did you do that?
Can you add gemini 3.5 flash it scored the highest on the financial benchmark so i wonder how it will do.
Nice one!
can you do one using a platform also usable by US residents?
My biggest issue with this test is that if the two models aren’t running at the same time, they’re not really trading the same market. Same prompt isn’t enough when volatility, liquidity and trend can change minute by minute. A fairer comparison would run both agents in parallel under identical constraints, ideally across multiple runs.
You didn’t show the strategy codex decided to use I don’t know if that was purposely or on accident
Can you do Forex EUR/USD it's very good for that and it's volatile so good opportunities
Brother , try Qwen 3.7 I think the framework is better on an hourly basis
Now we need to see how it goes with Opus 4.8 :D