Kimi K2 (0905) vs GLM-4.5
Moonshot AI Kimi K2 (0905) | Z.ai GLM-4.5 | |
|---|---|---|
| Overview | ||
| Company | Moonshot AI | Z.ai |
| Release date | Sep 5 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. | 65.8%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. | 75.1% | 79.1%Best |
| Timeline | ||
| Release gap | GLM-4.5 shipped 39 days before Kimi K2 (0905) | |
Which is better: Kimi K2 (0905) or GLM-4.5?
Kimi K2 (0905) and GLM-4.5 are evenly matched across the 2 benchmarks they both report (SWE-Bench Verified, GPQA Diamond). GLM-4.5 shipped 39 days before Kimi K2 (0905), so benchmark comparisons should account for the intervening progress.
Kimi K2 (0905) has 1T parameters, while GLM-4.5 has 355B. Context windows are 256k (Kimi K2 (0905)) vs 128k (GLM-4.5).
On SWE-Bench Verified, Kimi K2 (0905) leads at 65.8% vs GLM-4.5 at 64.2%. On GPQA Diamond, GLM-4.5 leads at 79.1% vs Kimi K2 (0905) at 75.1%.
Frequently asked questions
Kimi K2 (0905) was released by Moonshot AI on Sep 5 2025.
GLM-4.5 was released by Z.ai on Jul 28 2025.
Kimi K2 (0905) leads on SWE-Bench Verified — Kimi K2 (0905) 65.8% vs GLM-4.5 64.2%.
GLM-4.5 leads on GPQA Diamond — Kimi K2 (0905) 75.1% vs GLM-4.5 79.1%.
Kimi K2 (0905) has a 256k context window; GLM-4.5 has 128k.