Qwen 3.8 27BOpen weights

Data snapshot 2026-10-26

Overall score

48.8

Awaiting benchmarks (insufficient coverage)

Benchmark coverage

26.9%

7 third-party benchmarks

Context window

—

tokens

Input price

—

per million tokens

Output price

—

per million tokens

Dimension performance

Coding

51.1

Office

44.1

Above averageBelow averageAnchored at 50 (reference models’ average); every 15 points ≈ one standard deviation

Coding3 items

CyberBench Patch67.8

Vibe Code Bench64.85

ProgramBench0

Office3 items

Tax Eval v270.85

Legal Research36.06

MedCode28.7

Knowledge1 items

MMLU-Pro84.34

Multiple reasoning tiers of the same benchmark take the best value; raw scores have different scales and are not comparable across benchmarks.