MMODELYST
Models/Qwen2-72B-Instruct
MDL

Qwen2-72B-Instruct

Qwen

Parameters
72.7B
Downloads
Likes
Avg score
43.6
6 benchmarks
Weights
Open
Released
About

Qwen2-72B-Instruct is a 72.7B-parameter open-weights model in the Qwen2 family from Qwen. Benchmarked on 6 evals, averaging 43.6.

other
Benchmark scores · 6
avg 43.6 — higher is better
IFEval
79.9
BIG-Bench Hard
57.5
MMLU-Pro
48.9
MATH Lvl 5
41.8
MuSR
17.2
GPQA Diamond
16.3
The research behind this model
all papers mentioning it →

Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.

Details
PublisherQwen
FamilyQwen2
Parameters72.7B
Licenseother
WeightsOpen
Released
Capability over time

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