Claude Sonnet 4 now supports 1M tokens of context

Re:Claude Sonnet 4 now supports 1M tokens of context by jbellis on Tuesday August 12, 2025 @12:51PM (#44878889)

Just completed a new benchmark that sheds some light on whether Anthropic's premium is worth it.

(Short answer: not unless your top priority is speed.)

[ Parent | on HN ]

Re:Claude Sonnet 4 now supports 1M tokens of context by rcanepa on Tuesday August 12, 2025 @01:59PM (#44879751)

I recently switched to the $200 CC subscription and I think I will stay with it for a while. I briefly tested whatever version of ChatGPT 5 comes with the free Cursor plan and it was unbearably slow. I could not really code with it as I was constantly getting distracted while waiting for a response. So, speed matters a lot for some people.

[ Parent | on HN ]

Re:Claude Sonnet 4 now supports 1M tokens of context by 24xpossible on Tuesday August 12, 2025 @01:08PM (#44879121)

Why no Grok 4?

[ Parent | on HN ]

Re:Claude Sonnet 4 now supports 1M tokens of context by Zorbanator on Tuesday August 12, 2025 @02:54PM (#44880374)

You should be able to guess.

[ Parent | on HN ]

Re:Claude Sonnet 4 now supports 1M tokens of context by jeffhuys on Wednesday August 13, 2025 @02:39AM (#44885285)

People hate it because it had less filters and media caught on, so they told people to hate it.

It’s actually the best one right now, or close to. For my uses (code and queries) nothing comes even close.

Once people look past the “but ELoN mUssKkkk!!!”, they’ll be surprised.

[ Parent | on HN ]

Re:Claude Sonnet 4 now supports 1M tokens of context by jbellis on Wednesday August 13, 2025 @10:01AM (#44888567)

the accompanying blog post explains: xAI did not respond to our requests for a grok 4 quota that would allow us to run the evaluation

[ Parent | on HN ]