Kimi K2 vs GLM-4.6
Moonshot AI Kimi K2 | Z.ai GLM-4.6 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | Z.ai |
| Release date | Jul 11 2025 | Sep 30 2025 |
| Access | Open Weight | Open Weight |
| Specifications | ||
Parameters | 1T | 355B |
Context window | 128k | 200k |
| Benchmarks | ||
Nonsense detection BullshitBench v2Given a confidently-worded but nonsensical prompt, does the AI spot that it makes no sense and push back — instead of playing along and inventing an answer? The score is how often it clearly called out the nonsense. Higher is better. | 10% | — |
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. | 65.8% | 68%Best |
Science GPQA DiamondGraduate-level science questions in biology, physics, and chemistry — hard enough that subject-matter PhDs score around 65%. Higher is better. | 75.1% | — |
| Timeline | ||
| Release gap | Kimi K2 shipped 81 days before GLM-4.6 | |
Which is better: Kimi K2 or GLM-4.6?
GLM-4.6 leads Kimi K2 on 1 of the 1 benchmark they both report (SWE-Bench Verified). Kimi K2 shipped 81 days before GLM-4.6, so benchmark comparisons should account for the intervening progress.
Kimi K2 has 1T parameters, while GLM-4.6 has 355B. Context windows are 128k (Kimi K2) vs 200k (GLM-4.6).
On SWE-Bench Verified, GLM-4.6 leads at 68% vs Kimi K2 at 65.8%.
Frequently asked questions
Kimi K2 was released by Moonshot AI on Jul 11 2025.
GLM-4.6 was released by Z.ai on Sep 30 2025.
GLM-4.6 leads on SWE-Bench Verified — Kimi K2 65.8% vs GLM-4.6 68%.
Kimi K2 has a 128k context window; GLM-4.6 has 200k.