LLM Comparison
GLM-5.2 vs Kimi K2 Thinking
Side-by-side specs, pricing & capabilities · Updated September 2026
Price vs Intelligence
Add to comparison
2/6 modelsSame tier:
| Organization | ||
| OpenTools Score | 58 20.0 | 65 42.0 |
| Family | GLM | Kimi |
| Status | Current | Current |
| Release Date | — | Nov 2025 |
| Context Window | 1.0M tokens | 262K tokens |
| Input Price | $1.40/M tokens | $0.60/M tokens |
| Output Price | $4.40/M tokens | $2.50/M tokens |
| Pricing Notes | Artificial Analysis page reported Input $1.40 per 1M tokens, cache hit $0.26 per 1M tokens, Output $4.40 per 1M tokens, AA Briefcase Elo 1265.54, and median output speed 102.29 tokens/second for GLM-5.2 (max) during this run. Verify provider terms before production use. | Cache read: $0.1500/M tokens |
| Capabilities | textreasoninglong-context | textcodeextended-thinking |
| Max Output | 1.0M tokens | 262K tokens |
| API Identifier | glm-5.2-max | moonshotai/kimi-k2-thinking |
| Benchmarks | ||
| Artificial Analysis Intelligence Index v4.1 | 51.0858347714416Artificial Analysis model page | — |
| Artificial Analysis Intelligence Index v4.3 | 34https://artificialanalysis.ai/models/glm-5-2 | — |
| GPQA Diamond | 89.4949artificial-analysis | 83.8384artificial-analysis |
| SciCode | 51.1574artificial-analysis | — |
| Terminal-Bench 2.1 | 77.9026artificial-analysis | — |
| GPQA | — | 84.5https://huggingface.co/moonshotai/Kimi-K2-Thinking |
| MMLU-Pro | — | 84.6https://huggingface.co/moonshotai/Kimi-K2-Thinking |
| AIME 2025 | — | 94.6667artificial-analysis |
| View GLM-5.2 | View Kimi K2 Thinking | |
Cost Calculator
Enter your expected monthly token usage to compare costs.
| Model | Input | Output | Total / mo | vs Best |
|---|---|---|---|---|
| Kimi K2 ThinkingCheapest | $0.60 | $1.25 | $1.85 | — |
| GLM-5.2 | $1.40 | $2.20 | $3.60 | +95% |
Z.ai
GLM-5.2
GLM-5.2 (max) is a Z AI text model tracked by Artificial Analysis. The page reports a 1 million token context window, text input and text output, a 51.09 Artificial Analysis Intelligence Index, and measured output speed around 102 tokens per second.
Moonshot AI
Kimi K2 Thinking
Kimi K2 Thinking is a large language model from Moonshot AI. Supports up to 262,144 token context window. Available from $0.60/M input tokens.
More Comparisons
Looking for more AI models?
Browse All LLMs