MiMo-V2-Flash

Leaderboards

Where MiMo-V2-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 MiMo-V2-Flash has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #79 / 256

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

  83.7%

  Self-reported

• MMLU-Pro

  #26 / 142

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

  84.9%

  Self-reported

• AIME 2025

  #25 / 123

  Competition maths problems from the 2025 American Invitational Mathematics Exam.

  94.1%

  Self-reported

• SWE-Bench Verified

  #49 / 120

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

  73.4%

  Self-reported

• Humanity's Last Exam

  #67 / 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

  22.1%

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

• BrowseComp

  #43 / 68

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

  58.3%

  Self-reported · In the agents score

• LiveCodeBench v6

  #27 / 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.

  80.6%

  Self-reported

• Terminal-Bench 2.0

  #49 / 54

  Getting real work done in a command-line terminal.

  38.5%

  Self-reported

• SWE-bench Multilingual

  #23 / 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.

  71.7%

  Self-reported

• HMMT 2025

  #22 / 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

  84.4%

  Self-reported

• Terminal-Bench

  #19 / 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.

  30.5%

  Self-reported

• LongBench v2

  #9 / 24

  LongBench v2 is a benchmark designed to assess the ability of LLMs to handle long-context problems requiring deep understanding and reasoning across real-world multitasks. It consists of 503 challenging multiple-choice questions with contexts ranging from 8k to 2M words across six major task categories: single-document QA, multi-document QA, long in-context learning, long-dialogue history understanding, code repository understanding, and long structured data understanding.

  60.6%

  Self-reported

• Arena-Hard v2

  #1 / 19

  Arena-Hard-Auto v2 is a challenging benchmark consisting of 500 carefully curated prompts sourced from Chatbot Arena and WildChat-1M, designed to evaluate large language models on real-world user queries. The benchmark covers diverse domains including open-ended software engineering problems, mathematics, creative writing, and technical problem-solving. It uses LLM-as-a-Judge for automatic evaluation, achieving 98.6% correlation with human preference rankings while providing 3x higher separation of model performances compared to MT-Bench. The benchmark emphasizes prompt specificity, complexity, and domain knowledge to better distinguish between model capabilities.

  86.2%

  Self-reported

• MRCR

  #6 / 7

  MRCR (Multi-Round Coreference Resolution) is a synthetic long-context reasoning task where models must navigate long conversations to reproduce specific model outputs. It tests the ability to distinguish between similar requests and reason about ordering while maintaining attention across extended contexts.

  45.7%

  Self-reported

• Tau-bench

  #3 / 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.

  80.3%

  Self-reported