Unspecified · LIVEBENCH 2026-06-25
claude-haiku-5-5-xhigh-effort
Published benchmark results for this specific model configuration.
claude-haiku-5-5-xhigh-effortOverall score72.1 / 100
Cost / successful task$0.019USD · benchmark workload
Weight accessNot reported
Where this configuration performs
Category averages from the same release, on a 0–100 scale.
Task-level results
theory of mind76.9zebra puzzle98.0spatial94.0logic with navigation56.0code generation78.9code completion73.9javascript59.1typescript40.0python55.0AMPS Hard98.0integrals with game89.0math comp97.1olympiad87.0consecutive events71.0tablejoin49.2tablereformat98.0connections93.8plot unscrambling42.7typos54.0paraphrase62.5simplify62.8story generation73.6summarize67.0
Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.