Models / Compare /Kimi K3 vs GLM 5
Head to head
Kimi K3 vs GLM 5
Compared on live catalog data — pricing synced daily, benchmark scores with provenance.
The short version
- GLM 5 is cheaper to run hosted: $2.55/M output vs $15.00/M for Kimi K3 (5.9× difference at the cheapest tracked provider).
- Kimi K3 takes 1M tokens of context vs 205K for GLM 5.
- Kimi K3 has downloadable weights (OPEN*) so you can self-host it; we hold no downloadable copy of GLM 5, so it runs through a provider's API.
- Kimi K3 scores 1531.4745 via Max on Arena Coding vs 1497.4049 for GLM 5.
- Kimi K3 scores 1468.7657 via Max on Arena Creative Writing vs 1446.2097 for GLM 5.
| Spec | ||
|---|---|---|
| Vendor | Moonshot AI | Z.AI |
| Parameters | 2.8T / 104B | 754B |
| 1M | 205K | |
| Weights | OPEN* | OPEN |
| License | Custom licence | MIT License |
| Modality | text+image->text | text->text |
| Released | Jun 13, 2026 | Feb 11, 2026 |
| 1752.7 GBest | 475.3 GBest | |
| Cheapest hosted | $3.00 / $15.00 per 1M (Novita AI) | $0.95 / $2.55 per 1M (OpenRouter) |
| Tracked providers | 17 | 17 |
Kimi K3 — our take
Kimi K3 is Moonshot AI's flagship coding model with nearly 2.8 trillion parameters and a one-million-token request limit. Its measured coding performance sits at the frontier, though its custom licence carries restrictions and its agentic scores are thinly measured.
full breakdown →GLM 5 — our take
GLM 5 is a large downloadable text model from Z.AI with a permissive MIT licence and a 204,800-token request limit. It scores well on coding leaderboards and is available from nine different providers, though its total parameter count may overstate its actual per-token workload.
full breakdown →Need more columns? Use theinteractive comparison to add up to four models.