The Open-Source AI Stack
RSS
All models

Models · Compare

Qwen 2 72B Instruct vs Claude 3.5 Sonnet

Rows highlighted in warm gray are where the models differ. Numbers carry their as-of date and primary source.

Specs

Field A: Qwen 2 72B Instruct B: Claude 3.5 Sonnet
Released 2024-06-062024-06-20
Developer AlibabaAnthropic
Openness Source-availableProprietary
License Tongyi Qianwen LicenseProprietary
OSI-approved nono
Data released nono
Training code nono
Architecture denseunknown
Total params 72.7B
Active params
Experts
Context window 131K200K
Attention gqaunknown
Position enc. ropeunknown
Pretraining tokens
Post-training sft, rlhf, dporlhf, constitutional
Training hardware
$/M input $0.00
$/M output $0.00
Output tok/sec 0

Benchmarks

Missing scores render as not reported; never inferred. Bold highlights the leader per benchmark.

General reasoning

MMLU 82.3 2024-06-07
MMLU-Pro 64.4 2024-06-07
GPQA-Diamond 37.1 2026-05-21

Code

HumanEval 86.0 2024-06-07
LiveCodeBench 15.9 2026-05-21

Math

MATH 59.7 2024-06-07
AIME 2024 14.7 2026-05-21

Held-out / arena

IFEval 77.6 2024-06-07

Context · A

Predecessor to the Qwen 2.5 family. The 72B class brought 128K-token context via YaRN and added 27 multilingual languages to the pretraining mix, but Alibaba kept the 72B variant under the Tongyi Qianwen License while smaller siblings moved to Apache 2.0.

Context · B

The first Claude release to beat its own larger sibling (Claude 3 Opus) on most benchmarks. Established Artifacts, driving a wave of code-and-canvas product copies.

Qwen 2 72B Instruct detail → · Claude 3.5 Sonnet detail →