← Back to context Comment by qoez 10 months ago Lots of releases but very little actual performance increases 4 comments qoez Reply int_19h 10 months ago Sonnet and Gemini saw fairly substantial perf increases recenly mchusma 10 months ago Love Sonnet but 3.7 is not obviously an improvement over 3.5 in my real world usage. Gemini 2.5 pro is great, has replaced most others for me (Grok I use for things that require realtime answers) int_19h 10 months ago Are you comparing it with or without thinking? I'd say it's a fairly big improvement in long thinking mode. BriggyDwiggs42 10 months ago It does a lot better on philosophy questions.
int_19h 10 months ago Sonnet and Gemini saw fairly substantial perf increases recenly mchusma 10 months ago Love Sonnet but 3.7 is not obviously an improvement over 3.5 in my real world usage. Gemini 2.5 pro is great, has replaced most others for me (Grok I use for things that require realtime answers) int_19h 10 months ago Are you comparing it with or without thinking? I'd say it's a fairly big improvement in long thinking mode. BriggyDwiggs42 10 months ago It does a lot better on philosophy questions.
mchusma 10 months ago Love Sonnet but 3.7 is not obviously an improvement over 3.5 in my real world usage. Gemini 2.5 pro is great, has replaced most others for me (Grok I use for things that require realtime answers) int_19h 10 months ago Are you comparing it with or without thinking? I'd say it's a fairly big improvement in long thinking mode. BriggyDwiggs42 10 months ago It does a lot better on philosophy questions.
int_19h 10 months ago Are you comparing it with or without thinking? I'd say it's a fairly big improvement in long thinking mode.
Sonnet and Gemini saw fairly substantial perf increases recenly
Love Sonnet but 3.7 is not obviously an improvement over 3.5 in my real world usage. Gemini 2.5 pro is great, has replaced most others for me (Grok I use for things that require realtime answers)
Are you comparing it with or without thinking? I'd say it's a fairly big improvement in long thinking mode.
It does a lot better on philosophy questions.