All comparisons
Google-Proof Q&A 87.9 — MMLU PRO 87.1 88.9 Massive Multi-discipline Multimodal Understanding 84.3 80.7 Instruction-Following Evaluation 93.9 — BFCL 68.3 77.5 SWE-bench Pro — 41.8
Kimi K2.5 vs Claude Opus 4.5
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2026-03-15 | 2025-11-01 |
| Context window | 256K | 200K |
| Parameters | 1T (MoE, 384 experts) | — |
| Architecture | mixture of experts | decoder only |
| License | MIT | Proprietary |
| Knowledge cutoff | — | 2025-12 |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| Structured Outputs | ||
| Code execution | ||
Availability | ||
| Providers | ||
Benchmarks