Google · LIVEBENCH 2026-06-25

Gemini 3.5 Flash-Lite High

Published benchmark results for this specific model configuration.

gemini-3.5-flash-lite-high

Overall score63.9 / 100

Cost / successful task$0.069USD · benchmark workload

Weight accessNot reported

Where this configuration performs

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

Reasoning60.2

Coding76.1

Agentic Coding45.3

Mathematics73.7

Data Analysis53.2

Language71.8

Instruction Following67.2

Task-level results

theory of mind50.0zebra puzzle32.8spatial90.0logic with navigation68.0code generation76.1code completion76.1javascript59.1typescript26.7python50.0AMPS Hard95.0integrals with game26.0math comp92.2olympiad81.8consecutive events21.1tablejoin40.6tablereformat98.0connections92.0plot unscrambling49.5typos74.0paraphrase65.0simplify68.0story generation67.5summarize68.5

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