The honest view from inside technical leadership
LLM Leaderboard · Z.ai

GLM-5.3

Benchmarks, pricing and rank for GLM-5.3, with every score linked to the leaderboard that published it.

← All models

#2162.0CTO Index
Provider
Z.ai
Weights
Open weights
License
MIT
Price $/M in / out
$1.40 / $4.40
Context window
1M
Benchmarks covered
3 of 5

Benchmark results

Terminal-Bench 4.1Agentic coding
41.2%
#20 of 41 tracked · source
WebDev ArenaCoding (human-judged)
1623
#29 of 44 tracked · source
ARC-AGI-2Reasoning

No published result yet

Text ArenaGeneral chat (human-judged)
1482
#19 of 40 tracked · source
ARC-AGI-3Interactive reasoning

No published result yet

Snapshot 22 November 2026 · Scores copied from each benchmark's own leaderboard · How the CTO Index works

Compare GLM-5.3

Frequently asked questions

How good is GLM-5.3?

GLM-5.3 ranks #21 of 39 models on the Diary of a CTO Index with 62.0 points.

How much does GLM-5.3 cost?

GLM-5.3 lists at $1.40 / $4.40 per million input / output tokens.

What are GLM-5.3's benchmark scores?

Terminal-Bench 4.1: 41.2%; WebDev Arena: 1623; Text Arena: 1482.

What is GLM-5.3's context window?

GLM-5.3 supports a context window of 1M tokens.