LLM ReferenceLLM Reference
All comparisons

GPT-4 Turbo vs o3

Side-by-side comparison of specifications, capabilities, and pricing.

Released2024-04-092025-03-31
Context window128K128K
Parameters1.76T (8x222B MoE)*
Architecturemixture of expertsdecoder only
LicenseProprietaryUnknown
Knowledge cutoff2023-12

Capabilities

Vision
Multimodal
Reasoning
Function calling
Tool use
Structured Outputs
Code execution

Availability

Providers

Benchmarks

Massive Multitask Language Understanding86.5—Chatbot Arena1242.01412.0MMLU PRO69.4—HumanEval—96.7SWE-bench Verified—71.7LiveCodeBench—79.1Aider Polyglot—81.3Google-Proof Q&A—87.7Massive Multi-discipline Multimodal Understanding—82.9