GLM 4.7 vs Kimi K2.5

Z.ai · China  |  Moonshot AI · China · Updated June 2026

Quick verdict

Pick GLM 4.7 for genuinely permissive open weights — an mit-licensed 358b mixture-of-experts with no commercial restrictions or strong agentic coding for the price — 73.8% on swe-bench verified undercut most closed frontier models at launch. Pick Kimi K2.5 for native multimodal reasoning and visual coding or agentic tool-calling and self-directed multi-step work.

GLM 4.7 (Z.ai) and Kimi K2.5 (Moonshot AI) are two of the models people most often weigh against each other in 2026. GLM 4.7 is an MIT-licensed 358B open mixture-of-experts with strong 73.8% SWE-Bench Verified coding — but two generations behind GLM 5.2. Kimi K2.5 is moonshot's open-weight multimodal model at $0.60/$2.50 with a 256K window — strong visual coding and agentic work, since superseded by K2.6/K2.7. Their biggest split is context window, and the breakdown below shows exactly how that plays out for your workload.

Key differences at a glance

Side-by-side specs

SpecGLM 4.7Kimi K2.5
ProviderZ.ai (China) Moonshot AI (China)
ReleasedDecember 22, 2025 January 27, 2026
Context window200K (~304 pages) 256K (~393 pages)
Price (in/out)$0.6/$2.2 per 1M tokens $0.6/$2.5 per 1M tokens
Open weight?Yes — self-hostable Yes — self-hostable
Modalitiestext, code text, image, code
SWE-Bench Verified73.8% Not published
MRCR v2 @ 1MNot published Not published

Who wins what

Genuinely permissive open weights — an MIT-licensed 358B mixture-of-experts with no commercial restrictions

GLM 4.7

GLM 4.7 lists genuinely permissive open weights — an MIT-licensed 358B mixture-of-experts with no commercial restrictions among its strengths; Kimi K2.5 does not.

Strong agentic coding for the price — 73.8% on SWE-Bench Verified undercut most closed frontier models at launch

GLM 4.7

Kimi K2.5 is comparatively weak here — its coding score uses Moonshot's own harness, not the standard SWE-Bench Verified protocol

An unusually generous 128K maximum output, which suits bulk refactors and long generation

GLM 4.7

GLM 4.7 lists an unusually generous 128K maximum output, which suits bulk refactors and long generation among its strengths; Kimi K2.5 does not.

Native multimodal reasoning and visual coding

Kimi K2.5

Moonshot's open-weight multimodal model at $0.60/$2.50 with a 256K window — strong visual coding and agentic work, since superseded by K2.6/K2.7 — and it carries the larger 256K context.

Agentic tool-calling and self-directed multi-step work

Kimi K2.5

Moonshot's open-weight multimodal model at $0.60/$2.50 with a 256K window — strong visual coding and agentic work, since superseded by K2.6/K2.7 — and it is the newer of the two.

Open-weight (Modified-MIT) — self-hostable at 256K context

Kimi K2.5

Its 256K window holds about 1.3× more than GLM 4.7's 200K in a single prompt.

Largest single-prompt input

Kimi K2.5

Its 256K window is about 1.3× larger than GLM 4.7's 200K, fitting roughly 393 pages in one prompt.

Which should you pick?

Someone analysing very long documents or codebases

Kimi K2.5

Larger 256K window fits more in one prompt.

Anyone whose priority is genuinely permissive open weights — an mit-licensed 358b mixture-of-experts with no commercial restrictions

GLM 4.7

It is specifically built for that.

Anyone whose priority is native multimodal reasoning and visual coding

Kimi K2.5

That is its strongest area.

GLM 4.7: where it fits

An MIT-licensed 358B open mixture-of-experts with strong 73.8% SWE-Bench Verified coding — but two generations behind GLM 5.2. Released December 22, 2025 by Z.ai, it is built for genuinely permissive open weights — an MIT-licensed 358B mixture-of-experts with no commercial restrictions, strong agentic coding for the price — 73.8% on SWE-Bench Verified undercut most closed frontier models at launch, an unusually generous 128K maximum output, which suits bulk refactors and long generation, and cheap long-running agent loops thanks to aggressive prompt caching.

Its trade-offs are real: two generations behind — GLM 5, 5.1 and 5.2 have all shipped since, and new builds should default to those, its Verified lead narrows sharply on harder evaluations like SWE-Bench Pro, and text-only with no vision, and self-hosting a 358B model is a serious hardware commitment. At $0.6 in / $2.2 out per million tokens, it sits in the budget price band.

Kimi K2.5: where it fits

Moonshot's open-weight multimodal model at $0.60/$2.50 with a 256K window — strong visual coding and agentic work, since superseded by K2.6/K2.7. Released January 27, 2026 by Moonshot AI, it is built for native multimodal reasoning and visual coding, agentic tool-calling and self-directed multi-step work, open-weight (Modified-MIT) — self-hostable at 256K context, and vendor reports around 76.8% on its own SWE-agent coding harness.

Its trade-offs: its coding score uses Moonshot's own harness, not the standard SWE-Bench Verified protocol, superseded within Moonshot's line by Kimi K2.6 and K2.7, openRouter shows a promo price below Moonshot's $0.60/$2.50 list, and image input but no audio or video. At $0.6 in / $2.5 out per million tokens, it sits in the budget price band.

The bottom line for this matchup

GLM 4.7 and Kimi K2.5 overlap enough that the right pick depends on your specific job. Kimi K2.5 holds the larger context; and each leads in its own area — GLM 4.7 for genuinely permissive open weights — an mit-licensed 358b mixture-of-experts with no commercial restrictions, Kimi K2.5 for native multimodal reasoning and visual coding. Rather than crowning one, run the same hard task through both once and let the results decide.

Want both GLM 4.7 and Kimi K2.5 without two subscriptions? LumiChats gives you these plus 40+ models under one ₹69/day pass (about $1/day) — draft with one, cross-check with the other.

See pricing

Frequently asked questions

Is GLM 4.7 or Kimi K2.5 better for coding?

Public SWE-Bench figures are not available for Kimi K2.5, so the honest test is your own repository — run an identical real bug through both. By design, GLM 4.7 leans toward genuinely permissive open weights — an mit-licensed 358b mixture-of-experts with no commercial restrictions while Kimi K2.5 leans toward native multimodal reasoning and visual coding, and that positioning usually predicts which feels better on your codebase.

Which is cheaper, GLM 4.7 or Kimi K2.5?

They are priced almost identically, so cost will not decide between them.

Which has the bigger context window?

Kimi K2.5 — 256K vs 200K, about 1.3× larger. Useful only if the model actually reasons over the full window, which not all do.

Can I use both GLM 4.7 and Kimi K2.5 together?

Yes — a multi-model platform like LumiChats gives you GLM 4.7, Kimi K2.5 and 40+ others under one ₹69/day pass (about $1/day), so you can draft with one and cross-check with the other instead of buying two subscriptions.

Which is newer, GLM 4.7 or Kimi K2.5?

Kimi K2.5 — released January 27, 2026, about 36 days after GLM 4.7.

Related comparisons

Specifications and benchmarks reflect publicly reported figures as of June 2026 and may change as providers release updates. Always verify on your own workload.