Skip to main content
AITier

Qwen2.5 7B Instruct

Alibaba Cloud / Qwen TeamQwenOpen WeightApache 2.0 · Commercial OK

Description

Qwen2.5-7B-Instruct is an instruction-tuned 7B parameter language model that excels at following instructions, generating long texts (over 8K tokens), understanding structured data, and generating structured outputs like JSON. The model features enhanced capabilities in mathematics, coding, and multilingual support across 29+ languages including Chinese, English, French, Spanish, and more.

Release Date
2024-09-19
Parameters
7.6B
Context Length
33K
Modalities
text

Capability Radar

60
general
60
coding
70
reasoning
34
scienceest.
0
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

Biology

GPQA36.4%SR

Code

HumanEval84.8%SR
LiveCodeBench28.7%SR

Communication

MT-Bench0.88 / 100SR

Creativity

AlignBench73.3%SR
Arena Hard52.0%SR

Finance

MMLU-Pro56.3%SR

General

MBPP0.79 / 100SR
MMLU-Redux75.4%SR
IFEval71.2%SR
MultiPL-E70.4%SR
LiveBench35.9%SR

Math

GSM8k91.6%SR
MATH75.5%SR

AA Evaluation Indices

No AA evaluation data available

LLM Stats Category Scores

Communication
90
Roleplay
80
Structured Output
70
Creativity
70
Instruction Following
70
Language
70
Math
70
Writing
60
Code
60
Finance
60
General
60
Healthcare
60
Legal
60
Reasoning
60
Biology
40
Chemistry
40
Physics
40

Pricing

Input Price$0.04 / 1M tokens
Output Price$0.1 / 1M tokens
Blended Price (3:1)$0.055 / 1M tokens

Speed

No speed data available

Available Providers

(LS internal units)

No provider data available

External Sources

LLM Stats