GLM-5.1

Leaderboards

Where GLM-5.1 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-5.1 has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #61 / 256

  Graduate-level science questions written to be hard to look up.

  86.2%

  Self-reported

• Humanity's Last Exam

  #19 / 108

  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

  52.3%

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

• BrowseComp

  #21 / 68

  Finding hard-to-locate facts by browsing the web.

  79.3%

  Self-reported · In the agents score

• SWE-Bench Pro

  #26 / 61

  Harder, longer software engineering tasks from real codebases.

  58.4%

  Self-reported · In the coding score

• Terminal-Bench 2.0

  #11 / 54

  Getting real work done in a command-line terminal.

  69.0%

  Self-reported

• Toolathlon

  #34 / 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.

  40.7%

  Self-reported · In the agents score

• LiveBench

  #29 / 38

  LiveBench is a challenging, contamination-limited LLM benchmark that addresses test set contamination by releasing new questions monthly based on recently-released datasets, arXiv papers, news articles, and IMDb movie synopses. It comprises tasks across math, coding, reasoning, language, instruction following, and data analysis with verifiable, objective ground-truth answers.

  70.2%

  Self-reported · In the text score

• MCP Atlas

  #22 / 38

  MCP Atlas is a benchmark for evaluating AI models on scaled tool use capabilities, measuring how well models can coordinate and utilize multiple tools across complex multi-step tasks.

  71.8%

  Self-reported

• HMMT 2025

  #10 / 33

  Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds

  94.0%

  Self-reported

• Finance Agent v2

  #14 / 28

  Finance Agent v2 is an agentic financial-analysis benchmark from Vals that evaluates models on real-world finance workflows, measuring their ability to retrieve and reason over financial documents, perform multi-step calculations, and produce accurate analyses.

  44.8%

  Self-reported

• AIME 2026

  #6 / 26

  All 30 problems from the 2026 American Invitational Mathematics Examination (AIME I and AIME II), testing olympiad-level mathematical reasoning with integer answers from 000-999. Used as an AI benchmark to evaluate large language models' ability to solve complex mathematical problems requiring multi-step logical deductions and structured symbolic reasoning.

  95.3%

  Self-reported

• NL2Repo

  #18 / 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.

  42.7%

  Self-reported · In the coding score

• IMO-AnswerBench

  #12 / 22

  IMO-AnswerBench is a benchmark for evaluating mathematical reasoning capabilities on International Mathematical Olympiad (IMO) problems, focusing on answer generation and verification.

  83.8%

  Self-reported

• CyberGym

  #19 / 21

  CyberGym is a benchmark for evaluating AI agents on cybersecurity tasks, testing their ability to identify vulnerabilities, perform security analysis, and complete security-related challenges in a controlled environment.

  68.7%

  Self-reported

• FrontierSWE

  #12 / 16

  FrontierSWE measures whether an agent can complete open-ended technical projects at the scale of hours to tens of hours, spanning systems optimization, large-scale code construction, and applied ML research. Performance is reported as a dominance score, where higher is better.

  31.0%

  Self-reported

• HMMT Feb 26

  #13 / 13

  HMMT February 2026 is a math competition benchmark based on problems from the Harvard-MIT Mathematics Tournament, testing advanced mathematical problem-solving and reasoning.

  82.6%

  Self-reported

• TAU3-Bench

  #3 / 8

  TAU3-Bench is a benchmark for evaluating general-purpose agent capabilities, testing models on multi-turn interactions with simulated user models, retrieval, and complex decision-making scenarios.

  70.6%

  Self-reported

• Vending-Bench 2

  #2 / 4

  Vending-Bench 2 tests longer horizon planning capabilities by evaluating how well AI models can manage a simulated vending machine business over extended periods. The benchmark measures a model's ability to maintain consistent tool usage and decision-making for a full simulated year of operation, driving higher returns without drifting off task.

  563441.0%

  Self-reported