Unspecified · LIVEBENCH 2026-06-25

claude-haiku-5-5-max-effort

Published benchmark results for this specific model configuration.

claude-haiku-5-5-max-effort

Overall score67.9 / 100

Cost / successful task$0.051USD · benchmark workload

Weight accessNot reported

Where this configuration performs

Category averages from the same release, on a 0–100 scale.

Reasoning84.6

Coding77.9

Agentic Coding57.2

Mathematics86.4

Data Analysis51.8

Language62.6

Instruction Following54.7

Task-level results

theory of mind86.5zebra puzzle94.0spatial92.0logic with navigation66.0code generation77.5code completion78.3javascript68.2typescript43.3python60.0AMPS Hard97.0integrals with game67.0math comp98.0olympiad83.7consecutive events10.6tablejoin46.7tablereformat98.0connections96.0plot unscrambling27.9typos64.0paraphrase50.2simplify50.3story generation64.5summarize53.6

Source files: Scores ↗ Categories ↗ Costs ↗ . Missing cost is unknown, never free. Compare configurations within the same release.