Gemini 2.0 Flash

Leaderboards

Where Gemini 2.0 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 Gemini 2.0 Flash has a published result on, out of 100%, with its rank among the models that took it.

• GPQA

  #176 / 256

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

  62.1%

  Self-reported

• MMLU-Pro

  #75 / 142

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

  76.4%

  Self-reported

• LiveCodeBench

  #56 / 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.

  35.1%

  Self-reported

• MATH

  #5 / 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.

  89.7%

  Self-reported

• MMMU

  #32 / 66

  MMMU (Massive Multi-discipline Multimodal Understanding) is a benchmark designed to evaluate multimodal models on college-level subject knowledge and deliberate reasoning. Contains 11.5K meticulously collected multimodal questions from college exams, quizzes, and textbooks, covering six core disciplines: Art & Design, Business, Science, Health & Medicine, Humanities & Social Science, and Tech & Engineering across 30 subjects and 183 subfields.

  70.7%

  Self-reported

• FACTS Grounding

  #8 / 20

  A benchmark evaluating language models' ability to generate factually accurate and well-grounded responses based on long-form input context, comprising 1,719 examples with documents up to 32k tokens requiring detailed responses that are fully grounded in provided documents

  83.6%

  Self-reported

• HiddenMath

  #1 / 13

  Google DeepMind's internal mathematical reasoning benchmark that introduces novel problems not encountered during model training to evaluate true mathematical reasoning capabilities rather than memorization

  63.0%

  Self-reported

• Bird-SQL (dev)

  #2 / 9

  BIRD (BIg Bench for LaRge-scale Database Grounded Text-to-SQLs) is a comprehensive text-to-SQL benchmark containing 12,751 question-SQL pairs across 95 databases (33.4 GB total) spanning 37+ professional domains. It evaluates large language models' ability to convert natural language to executable SQL queries in real-world scenarios with complex database schemas and dirty data.

  56.9%

  Self-reported

• EgoSchema

  #5 / 9

  A diagnostic benchmark for very long-form video language understanding consisting of over 5000 human curated multiple choice questions based on 3-minute video clips from Ego4D, covering a broad range of natural human activities and behaviors

  71.5%

  Self-reported

• Natural2Code

  #1 / 8

  NaturalCodeBench (NCB) is a challenging code benchmark designed to mirror the complexity and variety of real-world coding tasks. It comprises 402 high-quality problems in Python and Java, selected from natural user queries from online coding services, covering 6 different domains.

  92.9%

  Self-reported

• Vibe-Eval

  #4 / 8

  VIBE-Eval is a hard evaluation suite for measuring progress of multimodal language models, consisting of 269 visual understanding prompts with gold-standard responses authored by experts. The benchmark has dual objectives: vibe checking multimodal chat models for day-to-day tasks and rigorously testing frontier models, with the hard set containing >50% questions that all frontier models answer incorrectly.

  56.3%

  Self-reported

• MRCR

  #4 / 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.

  69.2%

  Self-reported

• CoVoST2

  #2 / 4

  CoVoST 2 is a large-scale multilingual speech translation corpus derived from Common Voice, covering translations from 21 languages into English and from English into 15 languages. The dataset contains 2,880 hours of speech with 78K speakers for speech translation research.

  39.2%

  Self-reported