Anthropic · LIVEBENCH 2026-11-06
claude-sonnet-5.5
Published benchmark results for this specific model configuration.
claude-sonnet-5.5Overall score78.6 / 100
Cost / successful task$5.683USD · benchmark workload
Weight accessNot reported
Where this configuration performs
Category averages from the same release, on a 0–100 scale.
Task-level results
long agentic63.4reasoning91.6coding77.2browser89.3data analysis59.5research88.0design81.3
Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.