Gemini 3.7 Flash

Leaderboards

Where Gemini 3.7 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 3.7 Flash has a published result on, out of 100%, with its rank among the models that took it.

• CharXiv-R

  #10 / 60

  Reading and reasoning about charts from scientific papers.

  88.7%

  Self-reported

• DeepSWE 1.1

  #30 / 50

  DeepSWE 1.1 evaluates software engineering agents using the mini-swe-agent harness.

  65.3%

  Self-reported · In the coding score

• Terminal-Bench 2.1

  #12 / 46

  Terminal-Bench 2.1 is an updated release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal. It evaluates how well models handle real-world, end-to-end tasks autonomously, including compiling code, training models, setting up servers, system administration, data science workflows, and security tasks.

  85.8%

  Self-reported

• MRCR v2 (8-needle)

  #2 / 32

  MRCR v2 (8-needle) is a variant of the Multi-Round Coreference Resolution benchmark that includes 8 needle items to retrieve from long contexts. This tests models' ability to simultaneously track and reason about multiple pieces of information across extended conversations.

  97.0%

  Self-reported · In the text score

• LVBench

  #3 / 31

  LVBench is an extreme long video understanding benchmark designed to evaluate multimodal models on videos up to two hours in duration. It contains 6 major categories and 21 subcategories, with videos averaging five times longer than existing datasets. The benchmark addresses applications requiring comprehension of extremely long videos.

  85.4%

  Self-reported

• Agents' Last Exam

  #20 / 24

  Agents' Last Exam is a challenging benchmark for AI agents on hard, long-horizon tasks that test sustained reasoning, planning, and tool use, reported with and without tool access.

  26.3%

  Self-reported · In the agents score

• AutomationBench

  #15 / 24

  AutomationBench is a tool-use benchmark that evaluates AI agents on automating real-world workflows, testing their ability to orchestrate tools and complete multi-step automation tasks.

  30.4%

  Self-reported · In the agents score

• FrontierCode 1.1

  #11 / 23

  FrontierCode 1.1 evaluates whether coding-agent changes are mergeable, using unit tests, maintainer-defined rubrics, and verifiers. Runs flagged for unfair internet use receive a zero score.

  43.6%

  Self-reported · In the coding score

• OSWorld 2.0

  #14 / 17

  OSWorld 2.0 is a benchmark of 108 long-horizon, real-world computer-use workflows spanning everyday and professional tasks. Each task is an end-to-end workflow that takes human users a median of about 1.6 hours, scored with a binary-completion metric, and targets challenges such as dynamic environments, cross-source reasoning, and implicit-state inference.

  47.9%

  Self-reported

• GDP.pdf

  #3 / 14

  GDP.pdf is a knowledge-work vision benchmark that evaluates models on economically valuable professional tasks presented as visual documents (PDFs), testing document-based reasoning, chart and table interpretation, and problem solving without tools.

  34.0%

  Self-reported

• GDPval-AA

  #8 / 14

  GDPval-AA evaluates AI agents on economically valuable professional knowledge-work tasks and reports performance as an Elo score.

  50.8%

  Self-reported

• Artificial Analysis

  #3 / 13

  Artificial Analysis benchmark evaluates AI models across quality, speed, and pricing dimensions, providing a composite assessment of model capabilities for real-world usage.

  56.0%

  Self-reported

• BioMysteryBench

  #7 / 7

  BioMysteryBench evaluates a model's ability to reason through challenging molecular biology problems, reporting performance on a hard subset and on the subset of problems solved by human experts.

  43.5%

  Self-reported

• Harvey LAB-AA

  #1 / 5

  Harvey LAB-AA evaluates model performance on complex legal workflows.

  90.7%

  Self-reported

• Terminal-Bench 3.0

  #4 / 4

  Terminal-Bench 3.0 is a release of the Terminal-Bench benchmark that tests AI agents' ability to operate a computer via the terminal on real-world, end-to-end tasks.

  14.9%

  Self-reported

• HLE-Verified

  #2 / 3

  HLE-Verified evaluates multidisciplinary expert reasoning on a verified subset of Humanity's Last Exam.

  53.6%

  Self-reported

• LABBench2

  #3 / 3

  LABBench2 evaluates models on real-world biology research tasks.

  82.1%

  Self-reported

• WebDev Arena

  #1 / 1

  WebDev Arena is a leaderboard for evaluating AI models on web development tasks, including zero-shot generation, complex prompts, and interactive web UI creation. Models are ranked using Elo ratings based on their performance in coding and web development challenges.

  79.4%

  Unverified