toolcompass.

Find your next AI tool

Search by product name or task. Press Escape to close.

← All model benchmarks

Thinking Machines · LIVEBENCH 2026-06-25

Inkling xHigh Effort

Published benchmark results for this specific model configuration.

inkling-xhigh
Overall score71.9 / 100
Cost / successful task$0.310USD · benchmark workload
Weight accessOpen weights

Where this configuration performs

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

Reasoning78.3
Coding71.0
Agentic Coding49.4
Mathematics88.4
Data Analysis72.8
Language73.5
Instruction Following70.1

Task-level results

theory of mind65.4zebra puzzle88.0spatial94.0logic with navigation66.0code generation74.6code completion67.4javascript68.2typescript30.0python50.0AMPS Hard99.0integrals with game72.0math comp97.1olympiad85.4consecutive events69.9tablejoin48.5tablereformat100.0connections91.2plot unscrambling53.2typos76.0paraphrase70.8simplify60.5story generation74.2summarize74.8

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