Will Anthropic’s next Sonnet model exceed 65% on terminal bench? | Manifold

Will Anthropic’s next Sonnet model exceed 65% on terminal bench?

1

Ṁ100Ṁ10

Dec 31

45%

chance

1H

6H

1D

1W

1M

ALL

Will be looking toward https://www.tbench.ai/ for evals, using the terminus 2 scaffolding.

Only counts if the number in the model’s name increments, so a new Claude Sonnet 4.5 checkpoint does not count.

If a new Sonnet model is not released by 2027 this will resolve NA

Market context

Get

1,000

to start trading!

People are also trading

Will Anthropic’s next Sonnet model exceed 83% on SWE-bench verified?

When will an AI lab report 50% or better result on ZeroBench?

Have Claude Sonnet 4.5 model weights leaked before October 2025?

Will Anthropic ever drop out of the capabilities race despite ability to continue?

Will the next Claude Sonnet be better than Claude 4.5 Opus at software engineering?

Related questions

Will Anthropic’s next Sonnet model exceed 83% on SWE-bench verified?

When will an AI lab report 50% or better result on ZeroBench?

Have Claude Sonnet 4.5 model weights leaked before October 2025?

Will Anthropic ever drop out of the capabilities race despite ability to continue?

Will the next Claude Sonnet be better than Claude 4.5 Opus at software engineering?

© Manifold Markets, Inc.•Terms•Privacy