LLM ReferenceLLM Reference
All comparisons

Claude Sonnet 4.5 vs Kimi K2.5

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

Released2025-09-292026-03-15
Context window200K256K
Parameters1T (MoE, 384 experts)
Architecturedecoder onlymixture of experts
LicenseProprietaryMIT
Knowledge cutoff2025-12

Capabilities

Vision
Multimodal
Reasoning
Function calling
Tool use
Structured Outputs
Code execution

Availability

Providers

Benchmarks

Massive Multi-discipline Multimodal Understanding77.884.3BFCL73.268.3MMLU PRO86.087.1Google-Proof Q&A—87.9Instruction-Following Evaluation—93.9