Claude Sonnet 5 vs Claude Opus 4.8
Head-to-head technical comparison of intelligence, capabilities, and API pricing.
Which should you use?
Claude Sonnet 5 supersedes Claude Opus 4.8 in Anthropic's line-up, so this is an upgrade question rather than a bake-off.
Claude Sonnet 5 is also cheaper — $2 against $5 per 1M input tokens — so staying on Claude Opus 4.8 costs more for less.
Their Arena Elo differs by only 9 points, inside the confidence intervals the public board reports, so human preference does not separate them.
Cost is the sharper difference: Claude Opus 4.8 is 2.5x the input price of Claude Sonnet 5 ($5 against $2 per 1M), so at volume the choice is usually decided by budget rather than benchmarks.
Pick Claude Sonnet 5 when
- Stronger on MMLU-Pro: 94.6% against 94.5%.
- Cheaper input tokens — $2 against $5 per 1M, so Claude Opus 4.8 costs 2.5x as much to feed.
- Better value per point of measured capability: $0.021 per index point against $0.053.
Pick Claude Opus 4.8 when
On these measures Claude Opus 4.8 does not lead Claude Sonnet 5 anywhere, so pick it only for reasons outside this table — an existing integration, a region, or a contract.
Value per point of measured capability, at list input pricing: Claude Sonnet 5 $0.021 · Claude Opus 4.8 $0.053 per index point. Run your own token mix through the token cost calculator — a comparison at list price ignores caching and batch discounts, which move real bills more than this gap does.
Where these numbers come from
Figures as of 2026-09-14. Arena Elo and pricing are read from the public board and each vendor's own pricing page; see the full leaderboard for all 34 models and which columns are measured rather than estimated, or the benchmark matrix for scores benchmark by benchmark.
Our reporting on Anthropic
Build a Multi-Tool Claude Agent with MCP Servers in Python
Wire Claude to a local calculator, Brave search MCP server, and Anthropic-hosted tools in one extensible Python agent loop.
Claude Sonnet 5.5 Beats Opus 5.5 on Agentic Coding at Half the Tier Price
Anthropic's Sonnet 5.5 scores 70.6% on Terminal-Bench 4.0, outpacing Opus 5.5's 66.4%, at the same $2/$10 per-million-token price as Sonnet 5.
Claude Code Gets Plugin Evals: 6 Grader Types and a CI Gate
Claude Code v2.1.269 adds `claude plugin eval` with 6 grader types, a no-plugin baseline arm, and a CI threshold gate to measure whether skills actually fire.