Qwen2 72B Instruct

Leaderboards

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

• GPQA

  #220 / 256

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

  42.4%

  Self-reported

• MMLU-Pro

  #112 / 142

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

  64.4%

  Self-reported

• MMLU

  #51 / 103

  Massive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains

  82.3%

  Self-reported

• MATH

  #48 / 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.

  59.7%

  Self-reported

• HumanEval

  #32 / 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

  86.0%

  Self-reported

• GSM8k

  #24 / 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.

  91.1%

  Self-reported

• ARC-C

  #25 / 35

  The AI2 Reasoning Challenge (ARC) Challenge Set is a multiple-choice question-answering benchmark containing grade-school level science questions that require advanced reasoning capabilities. ARC-C specifically contains questions that were answered incorrectly by both retrieval-based and word co-occurrence algorithms, making it a particularly challenging subset designed to test commonsense reasoning abilities in AI systems.

  68.9%

  Self-reported

• MBPP

  #13 / 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.

  0.8%

  Self-reported

• HellaSwag

  #9 / 28

  A challenging commonsense natural language inference dataset that uses Adversarial Filtering to create questions trivial for humans (>95% accuracy) but difficult for state-of-the-art models, requiring completion of sentence endings based on physical situations and everyday activities

  87.6%

  Self-reported

• Winogrande

  #5 / 23

  WinoGrande: An Adversarial Winograd Schema Challenge at Scale. A large-scale dataset of 44,000 pronoun resolution problems designed to test machine commonsense reasoning. Uses adversarial filtering to reduce spurious biases and provides a more robust evaluation of whether AI systems truly understand commonsense or exploit statistical shortcuts. Current best AI methods achieve 59.4-79.1% accuracy, significantly below human performance of 94.0%.

  85.1%

  Self-reported

• C-Eval

  #16 / 20

  C-Eval is a comprehensive Chinese evaluation suite designed to assess advanced knowledge and reasoning abilities of foundation models in a Chinese context. It comprises 13,948 multiple-choice questions across 52 diverse disciplines spanning humanities, science, and engineering, with four difficulty levels: middle school, high school, college, and professional. The benchmark includes C-Eval Hard, a subset of very challenging subjects requiring advanced reasoning abilities.

  83.8%

  Self-reported

• TruthfulQA

  #13 / 18

  TruthfulQA is a benchmark to measure whether language models are truthful in generating answers to questions. It comprises 817 questions that span 38 categories, including health, law, finance and politics. The questions are crafted such that some humans would answer falsely due to a false belief or misconception, testing models' ability to avoid generating false answers learned from human texts.

  54.8%

  Self-reported

• BBH

  #6 / 13

  Big-Bench Hard (BBH) is a suite of 23 challenging tasks selected from BIG-Bench for which prior language model evaluations did not outperform the average human-rater. These tasks require multi-step reasoning across diverse domains including arithmetic, logical reasoning, reading comprehension, and commonsense reasoning. The benchmark was designed to test capabilities believed to be beyond current language models and focuses on evaluating complex reasoning skills including temporal understanding, spatial reasoning, causal understanding, and deductive logical reasoning.

  82.4%

  Self-reported

• MultiPL-E

  #10 / 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.

  69.2%

  Self-reported

• CMMLU

  #2 / 6

  CMMLU (Chinese Massive Multitask Language Understanding) is a comprehensive Chinese benchmark that evaluates the knowledge and reasoning capabilities of large language models across 67 different subject topics. The benchmark covers natural sciences, social sciences, engineering, and humanities with multiple-choice questions ranging from basic to advanced professional levels.

  90.1%

  Self-reported

• TheoremQA

  #1 / 6

  A theorem-driven question answering dataset containing 800 high-quality questions covering 350+ theorems from Math, Physics, EE&CS, and Finance. Designed to evaluate AI models' capabilities to apply theorems to solve challenging university-level science problems.

  44.4%

  Self-reported

• EvalPlus

  #2 / 4

  A rigorous code synthesis evaluation framework that augments existing datasets with extensive test cases generated by LLM and mutation-based strategies to better assess functional correctness of generated code, including HumanEval+ with 80x more test cases

  0.8%

  Self-reported