Kimi K2 Thinking vs GLM-4.5
Moonshot AI Kimi K2 Thinking | Z.ai GLM-4.5 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | Z.ai |
| Release date | Nov 6 2025 | Jul 28 2025 |
| Access | Open Weight | Open Weight |
| Specifications | ||
Parameters | 1T | 355B |
Context window | 256k | 128k |
| Benchmarks | ||
Coding SWE-Bench VerifiedReal coding tasks pulled from open-source projects — the AI has to find and fix actual bugs. A human-checked version of the original SWE-Bench. Higher is better. | 71.3%Best | 64.2% |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | — | 79.1% |
| Timeline | ||
| Release gap | GLM-4.5 shipped 101 days before Kimi K2 Thinking | |
Which is better: Kimi K2 Thinking or GLM-4.5?
Kimi K2 Thinking leads GLM-4.5 on 1 of the 1 benchmark they both report (SWE-Bench Verified). GLM-4.5 shipped 101 days before Kimi K2 Thinking, so benchmark comparisons should account for the intervening progress.
Kimi K2 Thinking has 1T parameters, while GLM-4.5 has 355B. Context windows are 256k (Kimi K2 Thinking) vs 128k (GLM-4.5).
On SWE-Bench Verified, Kimi K2 Thinking leads at 71.3% vs GLM-4.5 at 64.2%.
Frequently asked questions
Kimi K2 Thinking was released by Moonshot AI on Nov 6 2025.
GLM-4.5 was released by Z.ai on Jul 28 2025.
Kimi K2 Thinking leads on SWE-Bench Verified — Kimi K2 Thinking 71.3% vs GLM-4.5 64.2%.
Kimi K2 Thinking has a 256k context window; GLM-4.5 has 128k.
Other comparisons
Kimi K2 Thinking vs Claude Fable 5GLM-4.5 vs Claude Fable 5Kimi K2 Thinking vs GPT-5.6 SolGLM-4.5 vs GPT-5.6 SolKimi K2 Thinking vs Gemini OmniGLM-4.5 vs Gemini OmniKimi K2 Thinking vs Muse SparkGLM-4.5 vs Muse SparkKimi K2 Thinking vs Grok 4.3 BetaGLM-4.5 vs Grok 4.3 BetaKimi K2 Thinking vs DeepSeek-V4-ProGLM-4.5 vs DeepSeek-V4-Pro