llmboard.ai
Benchmarks
CompareRankings
llmboard.ai
Benchmarks
CompareRankings
HomeModelsQwen2 72B

Alibaba Cloud / Qwen Team model product

Qwen2 72B

Qwen2-72B-Instruct is an instruction-tuned language model with 72 billion parameters, supporting a context length of up to 131,072 tokens. It's part of the new Qwen2 series, which has surpassed most open-source models and demonstrates competitiveness against proprietary models across various benchmarks.

Updated Aug 10, 2026. Default version: Qwen2 72B Instruct

Compare
LLMBoard score38.0Qwen2 72B Instruct
Coverage80%13 benchmark families
Context windowN/ATokens
Official input priceN/AOfficial price unavailable

On this page

  • Specification
  • Capability
  • Benchmarks
  • Arena
  • Pricing
  • Versions
  • About
  • Compare
  • Similar models
  • FAQ

Model specification

Structured fields from the published default version.

Version
Qwen2 72B Instruct
Released
Jul 23, 2024
Knowledge cutoff
Unknown
Parameters
72B
Context window
N/A
Max output
N/A
Inputs
text
Outputs
text
Open weights
No
License
tongyi-qianwen

Capability profile

This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.

Qwen2 72B Instruct category scores

Benchmark results

Published benchmark records for the scored version Qwen2 72B Instruct.

17 rows
Columns

Show columns

TheoremQA0.416100.0%CAug 7, 2026
CMMLU0.92680.0%CAug 7, 2026
EvalPlus0.82466.7%CAug 7, 2026
Winogrande0.942285.7%CAug 7, 2026
BBH0.871245.5%CAug 7, 2026
HellaSwag0.982773.1%CAug 7, 2026
MultiPL-E0.7101325.0%CAug 7, 2026
MBPP0.8133766.7%CAug 7, 2026
TruthfulQA0.5131829.4%CAug 7, 2026
C-Eval0.8141823.5%CAug 7, 2026
ARC-C0.7243430.3%CAug 7, 2026
GSM8k0.9254848.9%CAug 7, 2026
HumanEval0.9367653.3%CAug 7, 2026
MATH0.6487132.9%CAug 7, 2026
MMLU0.84910051.5%CAug 7, 2026
MMLU-Pro0.610112921.9%CAug 7, 2026
GPQA0.419823315.1%CAug 7, 2026

Arena results

Preference and agent-evaluation signals from published Arena datasets.

56 rows
Columns

Show columns

text style controljapanese2131175.7901N/AAug 6, 2026
textjapanese2181111.4901N/AAug 6, 2026
text style controlfrench2321250.5596N/AAug 6, 2026
textfrench2331169.0596N/AAug 6, 2026
text style controlspanish2331245.6596N/AAug 6, 2026
textkorean2341082.81,167N/AAug 6, 2026
text style controlkorean2341171.61,167N/AAug 6, 2026
textspanish2371168.2596N/AAug 6, 2026
textchinese2461239.04,078N/AAug 6, 2026
text style controlgerman2461220.91,340N/AAug 6, 2026
text style controlchinese2471298.44,078N/AAug 6, 2026
textgerman2511150.71,340N/AAug 6, 2026
text style controlmath2511273.24,835N/AAug 6, 2026
text style controlindustry mathematical2521275.14,235N/AAug 6, 2026
textmath2591234.84,835N/AAug 6, 2026
textindustry mathematical2601230.74,235N/AAug 6, 2026
text style controlexpert2631258.61,763N/AAug 6, 2026
textexpert2701170.41,763N/AAug 6, 2026
text style controlindustry medicine and healthcare2701274.32,067N/AAug 6, 2026
text style controlhard prompts english2771284.16,483N/AAug 6, 2026
texthard prompts english2801207.66,483N/AAug 6, 2026
textindustry medicine and healthcare2801174.92,067N/AAug 6, 2026
text style controlhard prompts2801272.810,780N/AAug 6, 2026
textmulti turn2811195.56,698N/AAug 6, 2026
text style controlcoding2811296.76,249N/AAug 6, 2026
text style controlmulti turn2811243.26,698N/AAug 6, 2026
text style controlrussian2811237.04,555N/AAug 6, 2026
text style controlindustry legal and government2821273.22,262N/AAug 6, 2026
text style controlcreative writing2831222.55,504N/AAug 6, 2026
text style controlenglish2831275.419,928N/AAug 6, 2026
text style controlindustry entertainment and sports and media2831221.45,791N/AAug 6, 2026
text style controloverall2841261.337,325N/AAug 6, 2026
text style controlexclude ties2841170.923,757N/AAug 6, 2026
text style controlindustry life and physical and social science2841279.06,456N/AAug 6, 2026
text style controlindustry writing and literature and language2841241.69,976N/AAug 6, 2026
textindustry entertainment and sports and media2851166.25,791N/AAug 6, 2026
textindustry legal and government2851193.22,262N/AAug 6, 2026
textindustry writing and literature and language2851201.79,976N/AAug 6, 2026
text style controlindustry software and it services2851281.410,308N/AAug 6, 2026
textcoding2861196.36,249N/AAug 6, 2026
textenglish2861222.319,928N/AAug 6, 2026
textexclude ties2861087.823,757N/AAug 6, 2026
text style controlnon english2861238.517,397N/AAug 6, 2026
textcreative writing2871181.35,504N/AAug 6, 2026
texthard prompts2871190.910,780N/AAug 6, 2026
textinstruction following2871181.514,194N/AAug 6, 2026
textoverall2881203.537,325N/AAug 6, 2026
textlonger query2881192.64,614N/AAug 6, 2026
text style controlinstruction following2881241.614,194N/AAug 6, 2026
textindustry life and physical and social science2891195.66,456N/AAug 6, 2026
text style controllonger query2891260.74,614N/AAug 6, 2026
textnon english2901175.717,397N/AAug 6, 2026
textrussian2901167.94,555N/AAug 6, 2026
textindustry software and it services2921194.010,308N/AAug 6, 2026
text style controlindustry business and management and financial operations2941227.34,345N/AAug 6, 2026
textindustry business and management and financial operations2951146.14,345N/AAug 6, 2026

Pricing

Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.

Official API
N/A
Official provider
N/A
Lowest third-party
N/A
Tracked offerings
0
No published price snapshot

The default version has no provider offering with current input or output token prices.

Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.

Qwen2 72B versions

All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.

1 rows
Columns

Show columns

Qwen2 72B InstructJul 23, 202438.072BN/AN/ANotongyi-qianwen

What is Qwen2 72B?

A concise description based on the published model registry.

Qwen2-72B-Instruct is an instruction-tuned language model with 72 billion parameters, supporting a context length of up to 131,072 tokens. It's part of the new Qwen2 series, which has surpassed most open-source models and demonstrates competitiveness against proprietary models across various benchmarks.

Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.

Data snapshot: 2026-08-07. Editorial model content is not available in the backend.

Qwen2 72B vs nearby models

Open a comparison with the three ranked models immediately above and below this model.

Qwen2 72BvsJamba 1.5 LargeQwen2 72BvsDiffusionGemma 26B A4BQwen2 72BvsDeepSeek-V3Qwen2 72BvsPhi 4Qwen2 72BvsGemini 1.5 FlashQwen2 72BvsNova Micro

Models similar to Qwen2 72B

Recommendations prioritize the same model type and family, then the closest published LLMBoard score.

#115+1.7
AC

Qwen3 30B A3B

Alibaba Cloud / Qwen Team

39.7 LLMBoard

DetailsCompare
#124-1.9
AC

Qwen3.5 9B

Alibaba Cloud / Qwen Team

36.1 LLMBoard

DetailsCompare
#125-2.0
AC

Qwen3 VL 32B

Alibaba Cloud / Qwen Team

36.0 LLMBoard

DetailsCompare
#112+2.3
AC

Qwen3 Max

Alibaba Cloud / Qwen Team

40.3 LLMBoard

DetailsCompare
#111+2.3
AC

Qwen3 VL 30B A3B Thinking

Alibaba Cloud / Qwen Team

40.3 LLMBoard

DetailsCompare
#108+3.8
AC

Qwen3 Next 80B A3B

Alibaba Cloud / Qwen Team

41.8 LLMBoard

DetailsCompare

FAQ

Common questions about Qwen2 72B.

When was Qwen2 72B released?

Qwen2 72B's default version was released on Jul 23, 2024.

How much does Qwen2 72B cost?

No official standard PAYG price is currently available for Qwen2 72B.

Who created Qwen2 72B?

Qwen2 72B is published under Alibaba Cloud / Qwen Team in the model registry.

What is the context window for Qwen2 72B?

The current registry does not publish a context window for the default version.

Is Qwen2 72B open weight?

No. The default version is not marked as having publicly available weights.

How many API providers offer Qwen2 72B?

No published provider offering is currently linked to the default version.

What models should I compare Qwen2 72B with?

Nearby ranked alternatives include Jamba 1.5 Large, DiffusionGemma 26B A4B, DeepSeek-V3.

Rankings

OverallCodingText ArenaPricing

Modalities

Image GenerationVideo GenerationSpeech-to-TextEmbeddings

Benchmarks

All BenchmarksReasoningMathCoding

Vendors

All VendorsOpenAIAnthropicGoogle
llmboard.aiCopyright 2026 llmboard.ai