All comparisons
Massive Multi-discipline Multimodal Understanding 77.8 84.3 BFCL 73.2 68.3 MMLU PRO 86.0 87.1 Google-Proof Q&A — 87.9 Instruction-Following Evaluation — 93.9
Claude Sonnet 4.5 vs Kimi K2.5
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2025-09-29 | 2026-03-15 |
| Context window | 200K | 256K |
| Parameters | — | 1T (MoE, 384 experts) |
| Architecture | decoder only | mixture of experts |
| License | Proprietary | MIT |
| Knowledge cutoff | 2025-12 | — |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured Outputs | ||
| Code execution | ||
Availability | ||
| Providers | ||
Benchmarks