GLM-4.7

Leaderboards

Where GLM-4.7 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-4.7 has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #63 / 256

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

  85.7%

  Self-reported

• MMLU-Pro

  #31 / 142

  Broad knowledge and reasoning across 14 subjects, ten answer choices each.

  84.3%

  Self-reported

• AIME 2025

  #21 / 123

  Competition maths problems from the 2025 American Invitational Mathematics Exam.

  95.7%

  Self-reported

• SWE-Bench Verified

  #45 / 120

  Fixing real bugs in real GitHub projects, checked by the projects' own tests.

  73.8%

  Self-reported

• Humanity's Last Exam

  #34 / 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

  42.8%

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

• BrowseComp

  #48 / 68

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

  52.0%

  Self-reported · In the agents score

• LiveCodeBench v6

  #16 / 67

  LiveCodeBench is a holistic and contamination-free evaluation benchmark for large language models for code. It continuously collects new problems from programming contests (LeetCode, AtCoder, CodeForces) and evaluates four different scenarios: code generation, self-repair, code execution, and test output prediction. Problems are annotated with release dates to enable evaluation on unseen problems released after a model's training cutoff.

  84.9%

  Self-reported

• Terminal-Bench 2.0

  #47 / 54

  Getting real work done in a command-line terminal.

  41.0%

  Self-reported

• SWE-bench Multilingual

  #33 / 49

  A multilingual benchmark for issue resolving in software engineering that covers Java, TypeScript, JavaScript, Go, Rust, C, and C++. Contains 1,632 high-quality instances carefully annotated from 2,456 candidates by 68 expert annotators, designed to evaluate Large Language Models across diverse software ecosystems beyond Python.

  66.7%

  Self-reported

• Terminal-Bench

  #16 / 25

  Terminal-Bench is a benchmark for testing AI agents in real terminal environments. It evaluates how well agents can handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, security tasks, data science workflows, and cybersecurity vulnerabilities. The benchmark consists of a dataset of ~100 hand-crafted, human-verified tasks and an execution harness that connects language models to a terminal sandbox.

  33.3%

  Self-reported

• IMO-AnswerBench

  #15 / 22

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

  82.0%

  Self-reported

• BrowseComp-zh

  #6 / 15

  A high-difficulty benchmark purpose-built to comprehensively evaluate LLM agents on the Chinese web, consisting of 289 multi-hop questions spanning 11 diverse domains including Film & TV, Technology, Medicine, and History. Questions are reverse-engineered from short, objective, and easily verifiable answers, requiring sophisticated reasoning and information reconciliation beyond basic retrieval. The benchmark addresses linguistic, infrastructural, and censorship-related complexities in Chinese web environments.

  66.6%

  Self-reported

• Tau-bench

  #2 / 6

  τ-bench: A benchmark for tool-agent-user interaction in real-world domains. Tests language agents' ability to interact with users and follow domain-specific rules through dynamic conversations using API tools and policy guidelines across retail and airline domains. Evaluates consistency and reliability of agent behavior over multiple trials.

  87.4%

  Self-reported