GLM-5.3-Flash

Leaderboards

Where GLM-5.3-Flash sits among the top 20 in each category.

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Test results

Every test GLM-5.3-Flash has a published result on, out of 100%, with its rank among the models that took it.

• Humanity's Last Exam

  #14 / 115

  Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

  55.3%

  Self-reported · In the text score· In the vision score

• CharXiv-R

  #8 / 61

  Reading and reasoning about charts from scientific papers.

  89.4%

  Self-reported

• Terminal-Bench 2.1

  #16 / 53

  Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal. It evaluates how well models handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, data science workflows, and security tasks.

  84.3%

  Self-reported

• DeepSWE 1.1

  #32 / 52

  DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

  63.4%

  Self-reported · In the coding score

• Toolathlon

  #1 / 42

  Tool Decathlon is a comprehensive benchmark for evaluating AI agents' ability to use multiple tools across diverse task categories. It measures proficiency in tool selection, sequencing, and execution across ten different tool-use scenarios.

  78.4%

  Self-reported · In the agents score

• AutomationBench

  #7 / 27

  AutomationBench is a tool-use benchmark that evaluates AI agents on automating real-world workflows, testing their ability to orchestrate tools and complete multi-step automation tasks.

  48.8%

  Self-reported · In the agents score

• Agents' Last Exam

  #22 / 26

  Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.

  26.3%

  Self-reported · In the agents score

• NL2Repo

  #8 / 25

  NL2Repo evaluates long-horizon coding capabilities including repository-level understanding, where models must generate or modify code across entire repositories from natural language specifications.

  56.3%

  Self-reported · In the coding score

• BabyVision

  #14 / 18

  A benchmark for early-stage visual reasoning and perception on child-like vision tasks.

  53.4%

  Self-reported

• MVBench

  #1 / 18

  A comprehensive multi-modal video understanding benchmark covering 20 challenging video tasks that require temporal understanding beyond single-frame analysis. Tasks span from perception to cognition, including action recognition, temporal reasoning, spatial reasoning, object interaction, scene transition, and counterfactual inference. Uses a novel static-to-dynamic method to systematically generate video tasks from existing annotations.

  77.8%

  Self-reported

• GDPval-AA

  #2 / 17

  GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.

  59.1%

  Self-reported

• Artificial Analysis

  #2 / 13

  Artificial Analysis benchmark evaluates AI models across quality, speed, and pricing dimensions, providing a composite assessment of model capabilities for real-world usage.

  57.0%

  Self-reported

• OfficeQA Pro

  #9 / 13

  OfficeQA Pro evaluates AI models on professional knowledge-work questions and tasks drawn from real office workflows, including document analysis, spreadsheet reasoning, and information synthesis across business domains.

  62.4%

  Self-reported

• Chartography

  #7 / 7

  Chartography evaluates professional chart understanding with 100 expert-written tasks drawn from real charts across science, engineering, finance, manufacturing, supply chain, and healthcare.

  78.0%

  Self-reported

• MMVU

  #1 / 7

  MMVU (Multimodal Multi-disciplinary Video Understanding) is a benchmark for evaluating multimodal models on video understanding tasks across multiple disciplines, testing comprehension and reasoning capabilities on video content.

  80.5%

  Self-reported