Comprehensive side-by-side LLM comparison
UI-TARS-2 supports multimodal inputs. Both models have their strengths depending on your specific coding needs.
Alibaba / Qwen
Qwen2.5-72B-Instruct is the flagship of Alibaba's Qwen2.5 series, a 72-billion-parameter open-weight model released in September 2024 after training on 18 trillion tokens spanning code, mathematics, and multilingual text. It offers strong generalist performance across coding, instruction-following, and structured reasoning while remaining fully open-weight under Apache 2.0 — a combination that made it a widely referenced model in open-source evaluations and community benchmarking. The 128K context window and built-in structured output support made it a common choice for document analysis and multi-step agentic pipeline development.
ByteDance
UI-TARS-2, released by ByteDance in September 2025, is a major generational upgrade of the UI-TARS family of GUI interaction models, with enhanced capabilities across computer control, game environments, code generation, and tool use. It targets agentic workflows requiring robust multimodal understanding of graphical interfaces across diverse application domains.
11 months newer
Qwen2.5 72B Instruct
Alibaba / Qwen
2024-09-19
UI-TARS-2
ByteDance
2025-09-04
Available providers and their performance metrics
Qwen2.5 72B Instruct
UI-TARS-2
Qwen2.5 72B Instruct
UI-TARS-2