LLM Reference
All comparisons

Kimi K2.5 vs GPT-4o (05-13)

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

Released2026-03-152024-05-13
Context window256K128K
Parameters1T (MoE, 384 experts)1.76T (8x222B MoE)*
Architecturemixture of expertsmixture of experts
LicenseUnknownProprietary
Knowledge cutoff2023-10

Capabilities

Vision
Multimodal
Reasoning
Function calling
Tool use
JSON mode
Code execution

Availability

Providers

Benchmarks

HellaSwag—96.4HumanEval—90.2Massive Multitask Language Understanding—88.7