Internal evals put GPT 6.1 Sol on top: beats Claude Opus 5.5 at 40% cost, 2x speed

emilahlback · x · 2026-09-30

emilahlback reports that in their internal knowledge-work evals, GPT 6.1 Sol is the best model they've tested: it completed more work independently than Claude Opus 5.5, at 40% of the cost and nearly 2x the speed, leading in every industry measured. Note this is a third-party internal eval, not a public benchmark.

Related event: Internal Eval: GPT 6.1 Sol Beats Opus 5.5 at 40% of the Cost(3 posts)→

Original post →

More from Models

Models channel →