Model comparison
Hunyuan Hy4 preview vs GLM-5.2
- Input
- $0.834
- Output
- $2.501
- Context
- 1M
- Released
- 2026-08-28
- Input
- $1.40
- Output
- $4.40
- Context
- 1M
- Released
- 2026-06-16
Hunyuan Hy4 preview scores higher on 4 of the 4 benchmarks both models report; Hunyuan Hy4 preview is cheaper on input tokens ($0.8 vs $1.4 per 1M, 1.7×).
Specs and pricing side by side
| Spec | Hunyuan Hy4 preview | GLM-5.2 |
|---|---|---|
| Maker | Tencent | Z.ai (Zhipu / GLM) |
| Released | 2026-08-28 | 2026-06-16 |
| Context window | 1M | 1Msame |
| Max output | not published | 128K |
| Input price | $0.834 | $1.40 |
| Output price | $2.501 | $4.40 |
| Parameters | 770B total · 49B active | 744B total · 40B active |
| License | Apache-2.0 | MIT |
| Weights | Open weights | Open weightssame |
| Modalities | Text | Textsame |
Not published by either maker: knowledge cutoff.
Benchmarks both models report
| Benchmark | Hunyuan Hy4 preview | GLM-5.2 |
|---|---|---|
| GPQA Diamond | 92.3% | 91.2% |
| Terminal-Bench 2.1 | 85.4% | 82.7% |
| MCP-Atlas | 83.7% | 76.8% |
| SWE-bench Pro | 65.7% | 62.1% |
Scores are as published by each maker or its cited source; harness, reasoning effort and date can differ between rows, so treat small gaps as ties. Sources are listed on each model page.
Which one should you pick?
Pick Hunyuan Hy4 preview if…
- You care about GPQA Diamond, Terminal-Bench 2.1, MCP-Atlas (it scores higher on 4 shared benchmarks).
- Cost matters: input tokens cost 1.7× less ($0.8 vs $1.4 per 1M).
- Your use case is: self-hosted agentic coding and long-horizon software engineering via vLLM or SGLang.
Pick GLM-5.2 if…
- Your use case is: long-horizon, project-scale coding agents over large repositories.
FAQ
Which is better, Hunyuan Hy4 preview or GLM-5.2?
Hunyuan Hy4 preview scores higher on 4 of the 4 benchmarks both models report; Hunyuan Hy4 preview is cheaper on input tokens ($0.8 vs $1.4 per 1M, 1.7×). The better pick depends on whether you value benchmark scores, price per token, context length or openness for your workload.
How much cheaper is Hunyuan Hy4 preview?
Hunyuan Hy4 preview: $0.834 input, $2.501 output. GLM-5.2: $1.40 input, $4.40 output (list API prices as published by each maker).
What are the context windows of Hunyuan Hy4 preview and GLM-5.2?
Hunyuan Hy4 preview offers 1M; GLM-5.2 offers 1M with up to 128K output.
Is Hunyuan Hy4 preview newer than GLM-5.2?
Hunyuan Hy4 preview was released 2026-08-28; GLM-5.2 was released 2026-06-16.