Qwen3.5 2B
alibaba/qwen3.5-2b- Alibaba
- Family · Qwen3
- Released 2 Mar 2026
Not on OSMEXO yet
Scores · standing
Intelligence6.9#358/489
Coding2.9#193/196
News & trends
4 mentions this weekthis model · videos, posts, articles · 30 days
Trending · 14 days
- Qwen3 5 2B and Qwen3 8 2B benchmark and agentic coding test694 views
- LFM3-VL-2B vs. Qwen3.5-2B: Faster Multimodal Reasoning1.3K views
- "We let Qwen3.5-2B pick its own reward in RL. This ends up eliciting very diverse model personas, ranging from humany-talk 🧍, bliss ✨, universe lover 🪐, to the Guardian Angel of China 🛡️."5 upvotes
News · latest from Qwen3
- Memdoor: A team of 5 Qwen3.8-27B models beats Fable 5 on LiveCodeBench Hardgithub.com · 31 Oct
- Neuron Explorer for Qwen3.5-4B: See every neuron at work, make targeted editsgithub.com · 26 Oct
- How to train your own Jev for $17Together AI · 23 Sep
Benchmarks
bar = share of the top score · Benchmark data: Artificial AnalysisFamily progress
Intelligence Index
- Family releases33.7
Research papers
- DCKV: Learned Transform Coding of the Prompt KV Cache in Hybrid Language Models27 Oct
- DKnown-Jev: Fine-Tuning and Evaluation of a JEV-Style Model for Tasks Involving Normative Knowledge17 Oct
- Not Every User Says It All: Training Tool-Using Agents Beyond Ideal Simulated Users16 Oct
- What Survives When Activation Steering Is Used as Memory10 Oct
- Breaking the Space Barrier and its Application to Language Model Inference6 Oct
- Improving OCR Faithfulness via Gated and Attenuated On-Policy Distillation29 Sep
- Targeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning28 Sep
- HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement Learning12 Sep
Same family
Qwen3- 6.0
- 7.2
- 5.2
- 6.1
- 13.1
- 9.5
Alternatives
other vendors · similar capability- 8.5
- 11.6
- 10.0
- 6.7
Want Qwen3.5 2B on OSMEXO?
Sign in to request it. Requests are reviewed; a request does not guarantee availability.

