AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

Qwen2.5

Alibaba·

LLMsopen-weightcloud + localWorkstation

Overview

Flagship 72B model rivaling GPT-4o and Claude 3.5 on key benchmarks.

Capabilities and innovations

72B Parameters128k contextStructured outputTool usePost-training ScalingImproved Math & CodeLong-context Generation

Benchmarks

BenchmarkScoreSource
GPQA Diamond49%unsourced
SWE-bench Verified23%unsourced
MMLU88.5%unsourced
  • Humanity’s Last Exam (no tools): not reported by the vendor
  • SWE-bench Pro: benchmark did not exist at release
  • MMLU-Pro: benchmark did not exist at release
  • Terminal-Bench 2.x: benchmark did not exist at release
  • MMMU-Pro: benchmark did not exist at release

Architecture and hardware

Parameters
72B total (Dense)
Estimated VRAM at Q4
~42 GB, Workstation class

Links

More from Alibaba

Data curated by AI Model Timeline. See the methodology for admission criteria, benchmark eras and source priority.