AI Model Timeline

Tracking the accelerating release frequency of frontier AI models.

Qwen3

Alibaba·

LLMsopen-weightcloud + localMulti-GPU Self-Host

Overview

235B MoE flagship with hybrid thinking modes.

Capabilities and innovations

235B MoEHybrid thinking119 languages128k contextThinking/Non-thinking ModesMoE ArchitectureAgentic Coding

Benchmarks

BenchmarkScoreSource
GPQA Diamond68.9%unsourced
SWE-bench Verified42%unsourced
MMLU89.5%unsourced
  • Humanity’s Last Exam (no tools): not reported by the vendor
  • SWE-bench Pro: benchmark did not exist at release
  • MMLU-Pro: not reported by the vendor
  • Terminal-Bench 2.x: benchmark did not exist at release
  • MMMU-Pro: benchmark did not exist at release

Architecture and hardware

Parameters
235B total, 22B active per token (MoE)
Estimated VRAM at Q4
~136 GB, Multi-GPU Self-Host class

Links

More from Alibaba

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