Skip to content
gentic.news — AI News Intelligence Platform
Connecting to the Living Graph…
G
GPT-OSS-120B
stableNegative
vs
competes with (2)
Q
Qwen 3.5 4B
· quietNeutral
Coverage (30d)
1vs0
This Week
0vs0
Evidence
0 articles
Relationships
1
Share:

Timeline

GPT-OSS-120B2026-03-22

OpenAI released the 20-billion parameter GPT-OSS open-source model

GPT-OSS-120B2026-03-22

Technical guide published on fine-tuning GPT-OSS 20B using LoRA on MoE architecture

Qwen 3.5 4B2026-03-02

Qwen3.5 2B model successfully deployed to run locally on iPhone 17 Pro devices

Qwen 3.5 4B2026-03-02

Achieved benchmark scores of 82.5 on MMLU-Pro, 78.4 on MMMU, and 97.2 on CountBench

Ecosystem

GPT-OSS-120B

usesMixture of Experts (Sparse MoE for LLMs)1 src
usesSocialGrid1 src
usesPRL-Bench1 src
deploysChain-of-Thought Prompting1 src
deploysRotary Position Embedding (RoPE)1 src
deploysTransformer Self-Attention1 src

Qwen 3.5 4B

competes withGPT-OSS-120B2 src
usesiPhone 17 Pro1 src
usesMMLU-Pro1 src
usesMMMU1 src
usesCountBench1 src
GPT-OSS-120B vs Qwen 3.5 4B — AI Comparison 2026 | gentic.news