Comprehensive side-by-side LLM comparison
UI-TARS-72B-DPO supports multimodal inputs. Both models have their strengths depending on your specific coding needs.
OpenAI
GPT-5.1 Codex Max, released by OpenAI in November 2025, is an enhanced coding variant from the GPT-5.1 Codex line, designed for more complex software engineering tasks requiring additional reasoning depth. It targets large-scale code generation, automated refactoring, and sophisticated agentic development workflows.
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.
10 months newer
UI-TARS-72B-DPO
ByteDance
2025-01

GPT-5.1 Codex Max
OpenAI
2025-11
Available providers and their performance metrics
GPT-5.1 Codex Max
UI-TARS-72B-DPO
GPT-5.1 Codex Max
UI-TARS-72B-DPO