MiniMax M2

Leaderboards

Where MiniMax M2 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 MiniMax M2 has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #112 / 256

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

  78.0%

  Self-reported

• MMLU-Pro

  #46 / 142

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

  82.0%

  Self-reported

• AIME 2025

  #80 / 123

  Competition maths problems from the 2025 American Invitational Mathematics Exam.

  78.0%

  Self-reported

• SWE-Bench Verified

  #74 / 120

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

  69.4%

  Self-reported

• Humanity's Last Exam

  #90 / 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

  12.5%

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

• LiveCodeBench

  #8 / 76

  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.

  83.0%

  Self-reported

• BrowseComp

  #59 / 68

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

  44.0%

  Self-reported · In the agents score

• SWE-bench Multilingual

  #39 / 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.

  56.5%

  Self-reported

• Tau2 Telecom

  #17 / 36

  τ²-Bench telecom domain evaluates conversational agents in a dual-control environment modeled as a Dec-POMDP, where both agent and user use tools in shared telecommunications troubleshooting scenarios that test coordination and communication capabilities.

  87.0%

  Self-reported

• SciCode

  #26 / 30

  SciCode is a research coding benchmark curated by scientists that challenges language models to code solutions for scientific problems. It contains 338 subproblems decomposed from 80 challenging main problems across 16 natural science sub-fields including mathematics, physics, chemistry, biology, and materials science. Problems require knowledge recall, reasoning, and code synthesis skills.

  36.0%

  Self-reported

• Terminal-Bench

  #4 / 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.

  46.3%

  Self-reported

• BrowseComp-zh

  #13 / 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.

  48.5%

  Self-reported

• Multi-SWE-Bench

  #6 / 7

  A multilingual benchmark for issue resolving that evaluates Large Language Models' ability to resolve software issues across diverse programming ecosystems. Covers 7 programming languages (Java, TypeScript, JavaScript, Go, Rust, C, and C++) with 1,632 high-quality instances carefully annotated by 68 expert annotators. Addresses limitations of existing benchmarks that focus almost exclusively on Python.

  36.2%

  Self-reported

• Tau-bench

  #5 / 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.

  77.2%

  Self-reported

• AA-Index

  #3 / 4

  No official academic documentation found for this benchmark. Extensive research through ArXiv, IEEE/ACL/NeurIPS papers, and university research sites yielded no peer-reviewed sources for an 'aa-index' benchmark. This entry requires verification from official academic sources.

  61.0%

  Self-reported

• IF

  #2 / 2

  Instruction-Following Evaluation (IFEval) benchmark for large language models, focusing on verifiable instructions with 25 types of instructions and around 500 prompts containing one or more verifiable constraints

  72.0%

  Unverified