Anthropic · LIVEBENCH 2026-11-06
claude-haiku-5.5
Published benchmark results for this specific model configuration.
claude-haiku-5.5Overall score70.6 / 100
Cost / successful task$1.235USD · benchmark workload
Weight accessNot reported
Where this configuration performs
Category averages from the same release, on a 0–100 scale.
Task-level results
long agentic47.9reasoning82.4coding77.6browser69.5data analysis53.1research84.3design79.3
Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.