Claude Sonnet 5 – benchmark results

·Hacker News··

Analysis of Anthropic's Claude Sonnet 5 (Adaptive Reasoning, Max Effort) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Read full article →

Related Articles

OpenAI’s o1 correctly diagnosed 67% of ER patients vs. 50-55% by triage doctors
donsupreme · Hacker News · 1mo ago
Accelerating Gemma 4: faster inference with multi-token prediction drafters
amrrs · Hacker News · 1mo ago
Leanstral 1.5
vetronauta · Hacker News · 2h ago
A couple million lines of Haskell: Production engineering at Mercury
unignorant · Hacker News · 1mo ago
Using “underdrawings” for accurate text and numbers
samcollins · Hacker News · 2mo ago