Comprehensive side-by-side LLM comparison
o1-pro leads with 27.0% higher average benchmark score. o1-pro supports multimodal inputs. Overall, o1-pro is the stronger choice for coding tasks.
OpenAI
o1-pro was developed as an enhanced version of the o1 reasoning model, designed to provide extended reasoning capabilities with greater depth and reliability. Built for professionals and advanced users tackling complex analytical tasks, it offers enhanced thinking time and reasoning quality for the most demanding applications.
Microsoft
Phi-4 Mini Reasoning was developed to incorporate extended thinking capabilities into the ultra-compact Phi-4 Mini architecture. Built to demonstrate that reasoning enhancements can be applied even to very small models, it brings analytical depth to resource-constrained environments.
4 months newer

o1-pro
OpenAI
2024-12-17

Phi 4 Mini Reasoning
Microsoft
2025-04-30
Average performance across 1 common benchmarks

o1-pro

Phi 4 Mini Reasoning
o1-pro
2023-09-30
Phi 4 Mini Reasoning
2025-02-01
Available providers and their performance metrics

o1-pro

Phi 4 Mini Reasoning

o1-pro

Phi 4 Mini Reasoning