Claude Sonnet 5 is both more expensive and less intelligent than Opus 4.8, on Artificial Analysis Index
Summary
According to the Artificial Analysis Index, Claude Sonnet 5 is both more expensive and less intelligent than Opus 4.8.
Similar Articles
Claude Sonnet 5 is out and the gap with Opus 4.8 is smaller than I expected
Anthropic released Claude Sonnet 5, which achieves benchmark scores very close to Opus 4.8 at a significantly lower price, making it a compelling option for agentic tasks despite potential real-world gaps.
What's new in Claude Sonnet 5
Anthropic released Claude Sonnet 5, a model with performance near Opus 4.8 at lower prices, but featuring a new tokenizer that increases token counts for English and code by ~30%, effectively raising costs.
Claude Sonnet 5 Could Be Released Later Today, But May Not Be Better Than Opus 4.8
Claude Sonnet 5 may be released later today, featuring a new tokenizer, high-resolution vision, and marketed as Sonnet-priced near-Opus performance, but it may not exceed Opus 4.8.
Claude Sonnet 5
Anthropic releases Claude Sonnet 5, a highly agentic AI model with improved reasoning, tool use, and coding capabilities, narrowing the gap with Opus-level models at a lower price. It is available across all plans with introductory pricing.
Claude Sonnet 5 Artificial Analysis Results & Comparison
Provides analysis and comparison of Claude Sonnet 5's performance across benchmarks.