Google · LIVEBENCH 2026-06-25

Gemini 3.5 Flash High

Published benchmark results for this specific model configuration.

gemini-3.5-flash-high

Overall score74.6 / 100

Cost / successful task$0.249USD · benchmark workload

Weight accessNot reported

Where this configuration performs

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

Reasoning82.0

Coding78.2

Agentic Coding49.0

Mathematics88.2

Data Analysis64.9

Language84.6

Instruction Following75.6

Task-level results

theory of mind80.8zebra puzzle77.3spatial96.0logic with navigation74.0code generation80.3code completion76.1javascript63.6typescript33.3python50.0AMPS Hard98.0integrals with game68.0math comp95.1olympiad91.9consecutive events48.0tablejoin50.5tablereformat96.1connections100.0plot unscrambling67.8typos86.0paraphrase75.5simplify69.1story generation75.2summarize82.6

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