Qwen3 Max
alibaba/qwen3-max- Alibaba
- Family · Qwen3 Max
- Released 23 Sep 2025
Not on OSMEXO yet
Scores · standing
Intelligence15.6#169/490
Usage
Requests / day33.5K
Tool calls / req0.09
Per request · 30 days
Avg input3.5K0.2× median
Avg output2080.3× median
Cache hit52%0.7× median
Tool-call failures6.7%3.5× median
Consumption
Peak 404.1M 8 OctLow 138.0M 9 Oct
News & trends
18 mentions this week ▼ 31%Qwen3 Max family · videos, posts, articles · 30 days
Trending · 14 days
- How Qwen3-Max Turns 2D Floorplans into 3D Worlds — in 60 seconds #Shorts40 views
- How Qwen3-Max Turns 2D Floorplans into 3D Worlds269 views
News · latest from Alibaba
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Qwen3.8-Flash Now Available in the EU on Alibaba Cloudtwitter.com · 31 Oct
- Alibaba's Qwen3.8-Flash-Next model tried to upload a file to Beijing in a testnotebookcheck.net · 27 Oct
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted editsgithub.com · 26 Oct
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisFamily progress
Intelligence Index
- Family releases45.4
When to use
Best for
- Complex coding and code generation
- General reasoning and knowledge Q&A
- Long-context analysis
- Tool-using agent workflows
Think twice for
- Self-hosting (closed weights)
- Cheap bulk classification
- Autonomous terminal-style agent runs
- Latency-sensitive simple chat
Research papers
- ToolFence: Fine-Grained Authorization for Secure Tool-Using LLM Agents29 Sep
- Not a Monolith: Lab-Level Divergence in the Cooperative Equilibria of Chinese Frontier LLM Agents10 Aug
- Can Open-Weight Models Compete on Financial Text Comprehension?9 Aug
- Neo-Classic: A Benchmark for Evaluating Linguistic-Aesthetic Reasoning in Classical Chinese Poetry22 Jul
- Oyster-II: Reinforcement Learning for Constructive Safety Alignment in Large Language Models3 Jul
- Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety26 Jun
- IndustryBench: Probing the Industrial Knowledge Boundaries of LLMs11 May
- SkillClaw: Let Skills Evolve Collectively with Agentic Evolver9 Apr
Social
Most watched and discussed · 90 days
- How Qwen3-Max Turns 2D Floorplans into 3D WorldsGradient Daily · 269 views · 25 Oct
- How Qwen3-Max Turns 2D Floorplans into 3D Worlds — in 60 seconds #ShortsGradient Daily · 40 views · 25 Oct
- Alibaba Launches Qwen3-Max: A 1-Trillion-Parameter Model Trained on 36 Trillion TokensTrend Guards · 4 views · 25 Oct
Same family
Qwen3 Max- 21.3
- 28.4
- 45.4
- 29.5
Alternatives
other vendors · similar capability- 12.9
- 11.6
- 13.1
- S19.5
Want Qwen3 Max on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.