GLM-5.3-Flash.

Above the median score, but one of the slowest per task.

Z.ai · Open weights · Released 26 August 2026
Data from 13 November 2026.

  • Score28th of 58

    28

    Artificial Analysis's Intelligence Index. The median is 27.

  • Cost20th of 51

    $0.58

    What each task of that index costs. The median is $1.03.

  • Time47th of 50

    48.6 min

    How long each task of that index takes. The median is 14.6 min.

  • Context14th of 55

    1 million

    Tokens it reads at once, as 24 others do.

In short

It scores 28 on Artificial Analysis's Intelligence Index, 28th of the 58 models it scores. The median is 27.

Each task of that index costs it $0.58 and takes it 48.6 minutes on average. The median of the 58 is $1.03 and 14.6 minutes.

Z.ai sells it at $0.15 per million input tokens and $0.50 per million output tokens, and it reads up to 1 million tokens at once.

Its weights are published, so it can run on your own servers.

Its data

Maker
Z.ai
Weights
Open
Effort measured
Its only one
Price per million tokens
$0.15 input and $0.50 output
Context
1 million tokens
Released
26 Aug 2026

The score, the cost and the time per task and its tests from Artificial Analysis, read on 13 November 2026 at its highest effort. The price, the context and the release date from Z.ai's page. The table of the 58.

Its tests

Coding

  • FrontierCode 2.0 Changes to real open-⁠source projects. 28th of 58.17.6%
  • Terminal-⁠Bench 4.0 Complex work in the terminal, on its own. 20th of 58.32.8%

Reasoning

  • HLE Diamond Expert-⁠level questions. 26th of 58.18.2%
  • CritPt v2, hard subset Physics research problems. 33rd of 58.24.5%

Questions.

  • How much does GLM-5.3-Flash cost?

    Z.ai sells it at $0.15 per million input tokens and $0.50 per million output tokens. On the tasks of Artificial Analysis's index it costs $0.58 each.

  • How much text does it read at once?

    Up to 1 million tokens, according to Z.ai.

  • Can it run on your own servers?

    Yes. Its weights are published, so it can be downloaded and run on your own servers.

  • Which one for your company's software?

    It depends on the job. We cover it in “Which AI Model to Use to Build Your Company's Software”.

Let's talk.

Tell us what you need and one of the partners who write the code gets back to you.