Claude Opus 4.8 vs GPT-5.5

Claude Opus 4.8 edges ahead on overall intelligence (RunFree 94.7 vs 78.8). Here's how they stack up on benchmarks, price and specs.

Claude Opus 4.8
Anthropic
GPT-5.5
OpenAI

Shared benchmarks (2)

Loading chart…
Claude Opus 4.8GPT-5.5
RunFree Score94.778.8
Blended price / 1M$10.00$11.25
Input / 1M$5.00$5.00
Output / 1M$25.00$30.00
Context window1M1.1M
Max output128K128K
Reasoning modelYesYes
Humanity's Last Exam49.8%41.4%
Terminal-Bench74.6%78.2%
Wins42

A blank means the metric is tied or one model has no verified data. Prices are blended 3:1 input:output.

Compare more: Claude Opus 4.8 card · GPT-5.5 card · full leaderboard