Skip to main content

Models Deploy Leaderboards Marketplace

Track, rank, and compare every AI model in the world.

Platform

Models
Deploy
Leaderboards
Compare
News
Marketplace
Workspace
Deployments
Discover Watchlists
Pricing

Categories

LLMs
Image Gen
Vision
Multimodal
Embeddings
Speech
Video
Code
Browser Agents
Specialized

Company

About
Roadmap
Contact
FAQ
Providers
API
Terms
Privacy

© 2026 AI Market Cap. All rights reserved.

Qwen2.5-72B by Alibaba | AI Market Cap

Qwen2.5-72B

#175Large Language ModelsOpen Weights

A

Alibaba

Alibaba's strong open-weight model with excellent multilingual and coding performance.

Running this yourself: likely needs a high-memory cloud gpu.

Model updates refreshed4h agoJul 4, 2026news + changelog

View Updates Start Free Trial

63.4

Quality Score

1272

Arena ELO

72B

Parameters

131K

Context

Similar Models

DeepSeek-R1#184

Discussion (0)

Sign in to join the discussion

Loading comments...

2.8M

Downloads

4.5K

Likes

Sep 2024

Released

Benchmarks

19

high

Open Source

1

medium

What Changed Recently

Recent launch, pricing, benchmark, and API signals linked to this model or its provider.

BenchmarksToday

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

BenchmarksToday

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

Benchmarks & Rankings19

LeaderboardToday

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

Other

ollama-libraryAlibabaopen_sourceopen sourceToday

Qwen2.5-72B is now available on Ollama

77.0

Llama 4 Maverick#72

DeepSeek-V3.2#287

DeepSeek·Unknown

BenchmarksYesterday

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

BenchmarksYesterday

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

Benchmarks2d ago

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

LeaderboardToday

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

#benchmark#open-llm-leaderboard#💬 chat models (RLHF, DPO, IFT, ...)

LeaderboardYesterday

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

LeaderboardYesterday

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

#benchmark#open-llm-leaderboard#💬 chat models (RLHF, DPO, IFT, ...)

Leaderboard2d ago

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

Leaderboard2d ago

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

#benchmark#open-llm-leaderboard#💬 chat models (RLHF, DPO, IFT, ...)

Leaderboard3d ago

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

Leaderboard3d ago

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

#benchmark#open-llm-leaderboard#💬 chat models (RLHF, DPO, IFT, ...)

Leaderboard4d ago

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

Leaderboard4d ago

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

#benchmark#open-llm-leaderboard#💬 chat models (RLHF, DPO, IFT, ...)

Leaderboard5d ago

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

Leaderboard5d ago

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

#benchmark#open-llm-leaderboard#💬 chat models (RLHF, DPO, IFT, ...)

Leaderboard6d ago

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

Leaderboard6d ago

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

#benchmark#open-llm-leaderboard#💬 chat models (RLHF, DPO, IFT, ...)

Leaderboard1w ago

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

Leaderboard1w ago

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

#benchmark#open-llm-leaderboard#💬 chat models (RLHF, DPO, IFT, ...)

Leaderboard1w ago

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

Leaderboard1w ago

Qwen/Qwen2.5-72B-Instruct — Open LLM Leaderboard #6

Avg: 48.0 | IFEval: 86.4 | BBH: 61.9 | MATH: 59.8 | GPQA: 16.7 | MMLU-PRO: 51.4

#benchmark#open-llm-leaderboard#💬 chat models (RLHF, DPO, IFT, ...)

Leaderboard1w ago

Qwen/Qwen2.5-72B — Open LLM Leaderboard #377

Avg: 38.4 | IFEval: 41.4 | BBH: 54.6 | MATH: 39.1 | GPQA: 20.7 | MMLU-PRO: 55.2

#benchmark#open-llm-leaderboard#🟢 pretrained

Qwen2.5-72B is now available through local Ollama runtime. 32K context window listed. Qwen2.5 models are pretrained on Alibaba's latest large-scale dataset, encompassing up to 18 trillion tokens. The model supports up to 128K tokens and has multilingual support.

#deployability#ollama#alibaba