Skip to main content

Qwen2.5 Instruct 72B

AlibabaQwenOpen WeightQwen · Commercial OK

Description

Qwen2.5-72B-Instruct is an instruction-tuned 72 billion parameter language model, part of the Qwen2.5 series. It is designed to follow instructions, generate long texts (over 8K tokens), understand structured data (e.g., tables), and generate structured outputs, especially JSON. The model supports multilingual capabilities across over 29 languages.

Release Date
2024-09-19
Parameters
72.7B
Context Length
33K
Modalities
text

Capability Radar

80
general
70
coding
80
reasoning
43
scienceest.
77
agents
0
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Chat

MT-Bench0.94 / 100SR
IFEvalGoogle Research (2023)84.1%SR

General

AlignBench81.6%SR
Arena Hard81.2%SR
MultiPL-E75.1%SR

Language

MMLU-Redux86.8%SR
MMLU-Pro71.1%SR

Math

GSM8k95.8%SR
MATH83.1%SR
LiveBench52.3%SR

Reasoning

MBPP0.88 / 100SR
HumanEvalOpenAI (2021)86.6%SR
LiveCodeBench55.5%SR
GPQANYU + Cohere + Anthropic (2023)49.0%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Chat
90
Roleplay
90
Communication
90
Creativity
90
Instruction Following
80
Language
80
Math
80
Reasoning
80
Structured Output
80
General
80
Writing
80
Legal
70
Finance
70
Healthcare
70
Code
70
Physics
50
Biology
50
Chemistry
50

Pricing

Input Price$0.475 / 1M tokens
Output Price$0.495 / 1M tokens
Blended Price (3:1)$0.37 / 1M tokens

Speed

Tokens/sec32.6
Time to First Token3.18s
Time to Answer3.18s

Provider Price Ranking

Provider Price Ranking

5 providers

Cheapest: DeepInfraMost Expensive: Alibaba
ProviderInputOutput
1DeepInfraCheapest
$0.36
$0.4
2NanoGPT
$0.36
$0.4
3OpenRouter
$0.36
$0.4
4Kilo Gateway
$0.36
$0.4
5AlibabaPRIMARY
$0.475
$0.495

Compare pricing across different API providers for this model.

External Sources