Jordan Nanos is a member of technical staff at SemiAnalysis. His coauthored research compares open and closed AI models across technical eras.[1][2][3]
Start with Are Open Models Catching Up? →
Links
Publisher profile
X · JordanNanos Member of Technical Staff · SemiAnalysis
Contributions
Nanos and his coauthors distinguish scaling, reasoning and agentic models when comparing open and closed systems. Tests can saturate, so their analysis selects benchmarks for each period and combines results into capability scores. The historical trend depends on that evaluation protocol.[2]
Tools, writing & talks
Writing, research & talks
Start here
Are Open Models Catching Up?newsletter.semianalysis.comCompares open and closed models using era-specific benchmarks.
Read the measurement method before the charts. Familiarity with model benchmarks helps explain the comparison.
Coauthor with Evan Cloutier, Max Kan and Dylan Patel[2]SemiAnalysis discussion on subscription economics: a $200 Claude plan can yield about $12,000 of Opus 5.5 tokens at API pricing, versus roughly $5,000 to $6,000 on comparable ChatGPT plans, depending on workload and model.
Catalog workOriginal source