Anthropic · LIVEBENCH 2026-06-25

Claude Sonnet 5.5 xHigh Effort

Published benchmark results for this specific model configuration.

claude-sonnet-5-5-xhigh-effort

Overall score77.8 / 100

Cost / successful task$0.141USD · benchmark workload

Weight accessNot reported

Where this configuration performs

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

Reasoning86.8

Coding88.9

Agentic Coding39.3

Mathematics96.7

Data Analysis78.6

Language83.4

Instruction Following70.5

Task-level results

theory of mind69.2zebra puzzle100.0spatial98.0logic with navigation80.0code generation93.0code completion84.8javascript36.4typescript46.7python35.0AMPS Hard98.0integrals with game100.0math comp97.1olympiad91.7consecutive events90.9tablejoin46.9tablereformat98.0connections98.5plot unscrambling67.8typos84.0paraphrase62.3simplify72.4story generation77.1summarize70.3

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