Comprehensive side-by-side LLM comparison
UI-TARS-72B-DPO supports multimodal inputs. Both models have their strengths depending on your specific coding needs.
Microsoft
Phi-3.5-MoE-instruct is a sparse mixture-of-experts model from Microsoft's Phi research team, released in August 2024 with 42 billion total parameters across 16 experts and approximately 6.6 billion active parameters per forward pass. The model applies Microsoft's small-data, high-quality training philosophy — developed across earlier Phi generations — to a MoE architecture, targeting reasoning quality comparable to much larger dense models at a fraction of the inference compute. Released under the MIT license, it was notable in the research community for demonstrating that MoE efficiency gains could be realized at smaller total parameter counts than typical large-scale MoE deployments.
ByteDance
UI-TARS-72B-DPO, released by ByteDance in early 2025, is a 72 billion parameter multimodal large language model from the UI-TARS family, built on Qwen-2-VL and fine-tuned for automated GUI interaction and computer control. It features native understanding of screenshots, UI elements, and web interfaces, achieving strong results across GUI benchmarks for perception, grounding, and agentic control. UI-TARS-72B-DPO targets computer-use agents, web automation, and applications requiring robust visual UI reasoning.
4 months newer

Phi-3.5-MoE Instruct
Microsoft
2024-08-22
UI-TARS-72B-DPO
ByteDance
2025-01
Available providers and their performance metrics
Phi-3.5-MoE Instruct
UI-TARS-72B-DPO
Phi-3.5-MoE Instruct
UI-TARS-72B-DPO