Skip to main content

    Zhipu AI

    GLM-5.3

    Zhipu's August 14, 2026 coding and agentic model, built on the GLM-5.2 base with further post-training. Z.ai reports Terminal-Bench 3.0 of 28.3 and DeepSWE v1.1 of 66.9. Published weights use the custom GLM-5.3 license; hosted access is available through Z.ai and the GLM Coding Plan. Text-only input, a documented 1M-token context window and up to 128K output, with reasoning always enabled. Useful for coding teams that need long-running agents or self-hosted deployment under the model license.

    1M tokens
    Text only
    Pro
    New
    Provider
    Zhipu AI
    Context
    1M
    Catalog · As of Aug 24, 2026Within 30d
    yno subscription tier
    Pro
    Released
    Aug 14, 2026
    Speed
    Medium
    Reasoning
    Expert
    Modality
    Text only

    Benchmarks

    Quality

    AA Intelligence Index
    44.9points
    Artificial Analysis · Date unknownAge unknown
    AA Coding Index
    74.8points
    Artificial Analysis · Date unknownAge unknown
    GPQA Diamond
    91.7%
    Artificial Analysis · Date unknownAge unknown

    Speed and latency

    Output speed
    53.45tokens/s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first token
    2.99s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown
    Time to first answer token
    40.4s
    Configuration: Prompt length: 1,000 · Parallel queries: 1
    Artificial Analysis · Date unknownAge unknown

    API pricing

    API input cost
    $1.40/ 1M tokens
    Artificial Analysis · Date unknownAge unknown
    API output cost
    $4.40/ 1M tokens
    Artificial Analysis · Date unknownAge unknown

    Benchmark variant: GLM-5.3 (max)

    AA data retrieved Sep 11, 2026 · Artificial Analysis

    Indexes use points; evaluations use accuracy percentages. API measurements do not measure yno application performance. Methodology

    Capabilities

    • Code
    • Agentic
    • Reasoning
    • Long Horizon
    • Cyber Defense

    Use cases

    • Agentic coding
    • Terminal automation
    • Security analysis
    • Self-hosted coding agents

    Strengths

    • Vendor-reported DeepSWE v1.1 66.9
    • 1M context / 128K output
    • Hosted API and Coding Plan
    • Published weights; custom license

    Best for

    Coding teams building long-running agents with hosted or self-hosted deployment

    Use GLM-5.3 in yno.ai

    No credit card required

    Related models

    GLM-5.2

    Zhipu AI

    GLM-5.1

    Zhipu AI

    GLM-5

    Zhipu AI

    Frequently asked

    What is GLM-5.3?
    Zhipu's August 14, 2026 coding and agentic model, built on the GLM-5.2 base with further post-training. Z.ai reports Terminal-Bench 3.0 of 28.3 and DeepSWE v1.1 of 66.9. Published weights use the custom GLM-5.3 license; hosted access is available through Z.ai and the GLM Coding Plan. Text-only input, a documented 1M-token context window and up to 128K output, with reasoning always enabled. Useful for coding teams that need long-running agents or self-hosted deployment under the model license.
    How much does GLM-5.3 cost in yno.ai?
    GLM-5.3 is available on the Pro tier of yno.ai.
    What can GLM-5.3 do?
    GLM-5.3 is best for Coding teams building long-running agents with hosted or self-hosted deployment. Its main capabilities include Code, Agentic, Reasoning, Long Horizon, Cyber Defense.
    How does GLM-5.3 compare to other models?
    GLM-5.3 excels at Vendor-reported DeepSWE v1.1 66.9 and is recommended for Agentic coding, Terminal automation, Security analysis, Self-hosted coding agents. See related models below.
    How do I use GLM-5.3 in yno.ai?
    Sign up for yno.ai, select GLM-5.3 from the model picker, and start chatting.