logoalt Hacker News

cbg0 • today at 6:31 PM • 4 replies • view on HN

One of the things I'm always looking at with new models released is long context performance, and based on the system card it seems like they've cracked it:

  GraphWalks BFS 256K-1M

  Mythos     Opus     GPT5.4

  80.0%     38.7%     21.4%

Replies

metadat • today at 6:50 PM

Data source:

https://www-cdn.anthropic.com/53566bf5440a10affd749724787c89...

(Search for “graphwalk”.)

If true, the SWE bench performance looks like a major upgrade.

himata4113 • today at 6:58 PM

this seems to be similar to gpt-pro, they just have a very large attention window (which is why it's so expensive to run) true attention window of most models is 8096 tokens.

➕ show 2 replies
frog437 • today at 6:35 PM

[flagged]