Qwen2.5-32B-Instruct

Qwen

Parameters

32B

Downloads

on HF

Likes

354

Avg score

46.6

6 benchmarks

Weights

Open

Released

Sep 17, 2024

About

Qwen2.5-32B-Instruct is a 32B-parameter open-weights model in the Qwen2 family from Qwen. Benchmarked on 6 evals, averaging 46.6.

apache-2.0text-generation

Benchmark scores · 6

avg 46.6 — higher is better

IFEvalOpen LLM LB · 2026-05

83.5

MATH Lvl 5Open LLM LB · 2026-05

62.5

BIG-Bench HardOpen LLM LB · 2026-05

56.5

MMLU-ProOpen LLM LB · 2026-05

51.9

MuSROpen LLM LB · 2026-05

13.5

GPQA DiamondOpen LLM LB · 2026-05

11.7

The research behind this model

Details

PublisherQwen

FamilyQwen2

Parameters32B

Licenseapache-2.0

WeightsOpen

ReleasedSep 17, 2024

History

Capability over time

Append-only ledger — every observed change to this model's numbers.