Qwen2 Instruct 72B

AlibabaQwen開源權重tongyi-qianwen

描述

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.

發布日期

2024-06-07

參數規模

72.0B

上下文長度

—

支援模態

—

能力雷達圖

general

coding

reasoning

science

agents

multimodal

排行榜排名

領域	#排名	分數	來源
程式碼能力榜	535	17.0	AA
通用能力榜	527	26.0	AA
科學能力	584	18.0	AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

General

C-Eval

83.8%自報

MMLU

82.3%自報

MultiPL-E

69.2%自報

TruthfulQA

54.8%自報

Language

CMMLU

90.1%自報

MMLU-Pro

64.4%自報

Math

GSM8k

91.1%自報

MATH

59.7%自報

TheoremQA

44.4%自報

Reasoning

HellaSwagAI2 (2019)

87.6%自報

HumanEvalOpenAI (2021)

86.0%自報

Winogrande

85.1%自報

BBH

82.4%自報

MBPP

0.80 / 100自報

EvalPlus

0.79 / 100自報

ARC-C

68.9%自報

GPQANYU + Cohere + Anthropic (2023)

42.4%自報

AA 評測指數

(Artificial Analysis)

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

70.1

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

62.2

Gpqa(NYU + Cohere + Anthropic (2023))

37.1

Livecodebench(UC Berkeley + MIT + Cornell (2024))

15.9

Aime(MAA (Mathematical Association of America))

14.7

Intelligence Index(Artificial Analysis)

6.3

Hle(Center for AI Safety + Scale AI (2025))

3.7

LLM Stats 分類評分

(LLM Stats (zeroeval))

Language

Code

Legal

Math

Reasoning

General

Healthcare

Finance

Physics

Biology

Chemistry

定價

輸入價格免費

輸出價格免費

混合價格(3:1)免費

速度

Tokens/秒0.0

首Token延遲0.00s

首回答延遲0.00s

供應商價格排行

暫無提供商資料

外部連結

LLM Stats Artificial Analysis