Alibaba Cloud's Qwen 2.5 Tops OpenCompass LLM Leaderboard as the First Open-Source Champion

The article introduces Alibaba Cloud's open-source Qwen 2.5-72B-Instruct has achieved the top position on the OpenCompass large language model leaderboard.

compassbench
Qwen 2.5 tops OpenCompass LLM Leaderboard in its September update

According to its latest September update, Alibaba Cloud’s open-source Qwen 2.5-72B-Instruct has claimed the top spot on the OpenCompass large language model leaderboard. In various benchmarks,it surpasses even closed-source SOTA models, such as Claude 3.5 and GPT-4o.

Qwen 2.5-72B-Instruct showcased strong overall capabilities, achieving the highest score of 74.2 in coding and an impressive 77 in mathematics, outperforming Claude 3.5 (72.1) and GPT-4o (70.6). In a recent article, OpenCompass commended Qwen 2.5 as its first-ever open-source champion, reflecting the rapid progress in the open-source LLM community.

The bi-monthly leaderboard, established by the Shanghai Artificial Intelligence Laboratory, assesses LLM performance across language, knowledge, reasoning, mathematics, coding, instruction, and agent capabilities.

During the Apsara Conference 2024, Alibaba Cloud introduced over 100 open-source Qwen2.5 multimodal models to the global open-source community. These models range from 0.5 to 72 billion parameters in size and support over 29 languages.

See more about 100 open-sourced Qwen2.5 multimodal models on Apsara Conference 2024.

Watch the replay of the Apsara Conference 2024 at this link!

0 1 0

Share on

Community

Alibaba Cloud's Qwen 2.5 Tops OpenCompass LLM Leaderboard as the First Open-Source Champion

Read previous post:

Read next post:

Alibaba Cloud Community

You may also like

Comments

Alibaba Cloud Community

Related Products

Container Compute Service (ACS)

Container Service for Kubernetes

MaxCompute

Tongyi Qianwen (Qwen)