DeepSeek-V3.2-Exp

Leaderboards

Where DeepSeek-V3.2-Exp 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 DeepSeek-V3.2-Exp has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #104 / 256

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

  79.9%

  Self-reported

• MMLU-Pro

  #21 / 142

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

  85.0%

  Self-reported

• AIME 2025

  #52 / 123

  Competition maths problems from the 2025 American Invitational Mathematics Exam.

  89.3%

  Self-reported

• SWE-Bench Verified

  #79 / 120

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

  67.8%

  Self-reported

• Humanity's Last Exam

  #73 / 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

  19.8%

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

• LiveCodeBench

  #19 / 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.

  74.1%

  Self-reported

• BrowseComp

  #61 / 68

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

  40.1%

  Self-reported · In the agents score

• SWE-bench Multilingual

  #38 / 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.

  57.9%

  Self-reported

• SimpleQA

  #1 / 47

  SimpleQA is a factuality benchmark developed by OpenAI that measures the short-form factual accuracy of large language models. The benchmark contains 4,326 short, fact-seeking questions that are adversarially collected and designed to have single, indisputable answers. Questions cover diverse topics from science and technology to entertainment, and the benchmark also measures model calibration by evaluating whether models know what they know.

  97.1%

  Self-reported

• HMMT 2025

  #23 / 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

  83.6%

  Self-reported

• Terminal-Bench

  #11 / 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.

  37.7%

  Self-reported

• Aider-Polyglot

  #5 / 22

  A coding benchmark that evaluates LLMs on 225 challenging Exercism programming exercises across C++, Go, Java, JavaScript, Python, and Rust. Models receive two attempts to solve each problem, with test error feedback provided after the first attempt if it fails. The benchmark measures both initial problem-solving ability and capacity to edit code based on error feedback, providing an end-to-end evaluation of code generation and editing capabilities across multiple programming languages.

  74.5%

  Self-reported

• CodeForces

  #15 / 20

  A competitive programming benchmark using problems from the CodeForces platform. The benchmark evaluates code generation capabilities of LLMs on algorithmic problems with difficulty ratings ranging from 800 to 2400. Problems cover diverse algorithmic categories including dynamic programming, graph algorithms, data structures, and mathematical problems with standardized evaluation through direct platform submission.

  0.0%

  Self-reported

• BrowseComp-zh

  #14 / 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.

  47.9%

  Self-reported