All comparisons
HellaSwag 96.4 — HumanEval 90.2 — Massive Multitask Language Understanding 88.7 —
GPT-4o (05-13) vs Kimi K2.5
Side-by-side comparison of specifications, capabilities, and pricing.
| Released | 2024-05-13 | 2026-03-15 |
| Context window | 128K | 256K |
| Parameters | 1.76T (8x222B MoE)* | 1T (MoE, 384 experts) |
| Architecture | mixture of experts | mixture of experts |
| License | Proprietary | Unknown |
| Knowledge cutoff | 2023-10 | — |
Capabilities | ||
| Vision | ||
| Multimodal | ||
| Reasoning | ||
| Function calling | ||
| Tool use | ||
| JSON mode | ||
| Code execution | ||
Availability | ||
| Providers | ||
Benchmarks