Braintrust eval pits Opus 5.5 against GPT-6 Sol and Luna

Braintrust @braintrustOriginally posted 2026.09.23

Open original on X

Everyone is tired of reading AI slop. Anthropic says Opus 5.5 writes more naturally and actually follows instructions, so we ran an eval. We tested it against the new versions of OpenAI's GPT-6 Luna and Sol to see whether models can solve a problem AND write a decent explanation. Opus 5.5 came out on top in our tests, solving 80.1% of tasks and scoring 84.4% on writing quality. But Luna got to 78.0% and 83.8% for roughly 2% of the cost. Test them on your own tasks to see whether the difference matters. Read more → https://braintrustdata.link/opus-55-vs-gpt-6