Qwen2.5 72B Instruct

Leaderboards

Where Qwen2.5 72B Instruct 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 Qwen2.5 72B Instruct has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #203 / 256

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

  49.0%

  Self-reported

• MMLU-Pro

  #91 / 142

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

  71.1%

  Self-reported

• LiveCodeBench

  #40 / 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.

  55.5%

  Self-reported

• MATH

  #15 / 71

  MATH dataset contains 12,500 challenging competition mathematics problems from AMC 10, AMC 12, AIME, and other mathematics competitions. Each problem includes full step-by-step solutions and spans multiple difficulty levels (1-5) across seven mathematical subjects including Prealgebra, Algebra, Number Theory, Counting and Probability, Geometry, Intermediate Algebra, and Precalculus.

  83.1%

  Self-reported

• IFEval

  #44 / 70

  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

  84.1%

  Self-reported

• HumanEval

  #31 / 66

  A benchmark that measures functional correctness for synthesizing programs from docstrings, consisting of 164 original programming problems assessing language comprehension, algorithms, and simple mathematics

  86.6%

  Self-reported

• MMLU-Redux

  #34 / 50

  An improved version of the MMLU benchmark featuring manually re-annotated questions to identify and correct errors in the original dataset. Provides more reliable evaluation metrics for language models by addressing dataset quality issues found in the original MMLU.

  86.8%

  Self-reported

• GSM8k

  #10 / 48

  Grade School Math 8K, a dataset of 8.5K high-quality linguistically diverse grade school math word problems requiring multi-step reasoning and elementary arithmetic operations.

  95.8%

  Self-reported

• LiveBench

  #34 / 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.

  52.3%

  Self-reported · In the text score

• MBPP

  #5 / 33

  MBPP (Mostly Basic Python Problems) is a benchmark of 974 crowd-sourced Python programming problems designed to be solvable by entry-level programmers. Each problem consists of a task description, code solution, and 3 automated test cases covering programming fundamentals and standard library functionality.

  0.9%

  Self-reported

• Arena Hard

  #7 / 27

  Arena-Hard-Auto is an automatic evaluation benchmark for instruction-tuned LLMs consisting of 500 challenging real-world prompts curated by BenchBuilder. It includes open-ended software engineering problems, mathematical questions, and creative writing tasks. The benchmark uses LLM-as-a-Judge methodology with GPT-4.1 and Gemini-2.5 as automatic judges to approximate human preference. Arena-Hard achieves 98.6% correlation with human preference rankings and provides 3x higher separation of model performances compared to MT-Bench, making it highly effective for distinguishing between models of similar quality.

  81.2%

  Self-reported

• MT-Bench

  #3 / 13

  MT-Bench is a challenging multi-turn benchmark that measures the ability of large language models to engage in coherent, informative, and engaging conversations. It uses strong LLMs as judges for scalable and explainable evaluation of multi-turn dialogue capabilities.

  0.9%

  Self-reported

• MultiPL-E

  #7 / 13

  MultiPL-E is a scalable and extensible system for translating unit test-driven code generation benchmarks to multiple programming languages. It extends HumanEval and MBPP Python benchmarks to 18 additional programming languages, enabling evaluation of neural code generation models across diverse programming paradigms and language features.

  75.1%

  Self-reported

• AlignBench

  #2 / 5

  AlignBench is a comprehensive multi-dimensional benchmark for evaluating Chinese alignment of Large Language Models. It contains 8 main categories: Fundamental Language Ability, Advanced Chinese Understanding, Open-ended Questions, Writing Ability, Logical Reasoning, Mathematics, Task-oriented Role Play, and Professional Knowledge. The benchmark includes 683 real-scenario rooted queries with human-verified references and uses a rule-calibrated multi-dimensional LLM-as-Judge approach with Chain-of-Thought for evaluation.

  81.6%

  Self-reported