Skip to main content
Launching the open-source gateway

GLM-5 vs Hy3 preview

SpecGLM-5Hy3 preview
Respan Index27.7 (#88)28.7 (#87)
Blended price per 1M$1.33$0.285
Context window200K256K
Input / output per 1M$0.92 / $2.55$0.18 / $0.6
Max output131K-
Inputtexttext
Released-2026-04-23

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryGLM-5Hy3 preview
Coding10.4 GLM-511.6 Hy3 preview
Agents35.0 GLM-536.8 Hy3 preview
Reasoning25.3 GLM-527.2* Hy3 preview
Knowledge & language22.8* GLM-524.0* Hy3 preview
Human preference51.6 GLM-549.3 Hy3 preview

* Estimated: no published scores in that category. How the Respan Index works

Benchmarks both report

GLM-5 leads on 4 of the 4 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkGLM-5Hy3 preview
LMArena Elo14571409
LMArena WebDev (LMArena)14361357
SWE-bench Verified77.8%74.4%
Terminal-Bench 2.056.2%54.4%

FAQ

Is GLM-5 better than Hy3 preview?

Hy3 preview scores 28.7 on the Respan Index (#87), ahead of GLM-5 at 27.7 (#88). GLM-5 leads on 4 of the 4 benchmarks both report.

Which is cheaper, GLM-5 or Hy3 preview?

GLM-5 lists at $0.92 input and $2.55 output per 1M tokens; Hy3 preview at $0.18 and $0.6. Hy3 preview is 4.7x cheaper per token at list price.

Which has the larger context window?

GLM-5 accepts 200K tokens and Hy3 preview 256K tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.