Alibaba · LIVEBENCH 2026-06-25

Qwen 3.6 27B

Published benchmark results for this specific model configuration.

qwen3.6-27b

Overall score64.0 / 100

Cost / successful task$0.202USD · benchmark workload

Weight accessOpen weights

Where this configuration performs

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

Reasoning70.3

Coding71.8

Agentic Coding39.3

Mathematics79.9

Data Analysis70.4

Language63.3

Instruction Following53.2

Task-level results

theory of mind65.4zebra puzzle53.8spatial100.0logic with navigation62.0code generation71.8code completion71.7javascript54.5typescript23.3python40.0AMPS Hard93.0integrals with game52.0math comp92.2olympiad82.3consecutive events70.4tablejoin42.8tablereformat98.0connections77.2plot unscrambling42.7typos70.0paraphrase49.4simplify50.7story generation60.1summarize52.6

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