Mercury 2.5 LLM hits 770 tokens per second
Artificial Analysis lists Mercury 2.5 at 770 tokens per second on its model benchmark page.
Artificial Analysis's model page for Mercury 2.5 is headlined as reaching 770 tokens per second. The extracted page content mainly describes Intelligence Index v4.3.2, which combines 10 evaluations including AA-Briefcase, GDPval-AA, Terminal-Bench 4.0, SciCode, and Humanity's Last Exam. Specific index scores, pricing, and context-window figures for Mercury 2.5 are not included in the extracted text.
- Headline speed claim is 770 tokens per second.
- Page uses Artificial Analysis Intelligence Index v4.3.2.
- Index covers 10 evaluations, including coding and science tests.
- Extracted text omits Mercury 2.5's intelligence score.
- Organizations
- Artificial Analysis
- AI models
- Mercury 2.5
From the original article
5 min read at artificialanalysis.aiArtificial Analysis Intelligence Index v4. 3. 2 incorporates 10 evaluations: AA-Briefcase v1.
By Retro_Dev · artificialanalysis.ai
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.