Phi 4 vs GLM 4.6
Phi 4 is cheaper on output tokens, while GLM 4.6 offers a larger context window. Choose Phi 4 or GLM 4.6 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | Phi 4 | GLM 4.6 |
|---|---|---|
| Provider | Microsoft | Z.ai |
| Input / 1M tokens | $0.07 | $0.55 |
| Output / 1M tokens | $0.14 | $2.20 |
| Context window | 16K | 205K |
| Parameters | — | 357B |
| Open weights | — | Yes |
| Released | — | Sep 2025 |
| Epoch Capabilities Index score | 130 | — |
| LMArena (Chatbot Arena) Elo score | 1217 | 1440 |
| GPQA Diamond score | 56.1 | — |
| LiveBench score | — | 54.7 |
| SWE-bench Verified score | — | 68.2 |
| FrontierMath score | — | 3.8 |
| LMArena WebDev Elo score | — | 1341 |
FAQ
Is Phi 4 or GLM 4.6 cheaper?
Phi 4 is cheaper on output tokens ($0.14 vs $2.20 per 1M).
Which has the larger context window, Phi 4 or GLM 4.6?
GLM 4.6 has the larger context window (205K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.