Sonnet 5.5 scores just behind Opus 5.5 on Artificial Analysis Intelligence Index

Anthropic's new Sonnet model scores 56, just 2 points behind Opus 5.5 (max), but at the highest Output Tokens per Task we have measured

3 points•spenvo•2 days ago•1 comment•

1 comment

It’s better than both fable and Astra? I’m going to start trusting this index less and less.

jug1 day ago

It's apparently great at Max but extremely costly. Looks best to me at Medium and High. Over that and I'd go Opus. I consider Fable largely obsolete.

simianwordsabout 21 hours ago

Astra at light is worse than sol at light tbh

ramon1562 days ago

the issue is, what will we use? companies are benchmaxxing, so how do you make a bench that cannot be cheated?

Human curated benches aren't accurate enough

The problem with benchmarks is that they are end to end.

You go from one prompt to the final solution, whereas for many of us it is about the experience of iterative, multi turn working.