Skip to content

Google Proprietary Released Jul 21, 2026 Updated

Gemini 3.6 Flash

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #29 / 416

    537 / 1,000

    ToolsGuide Score· votes only

  • Vision #28 / 167

    538 / 1,000

    ToolsGuide Score· votes only

  • Coding #56 / 147

    363 / 1,000

    ToolsGuide Score· votes 390, tests 345

  • Price per 1M tokens

    In $1.50· Out $7.50

    $1.50

    Input · median text model $0.43

Summary

Gemini 3.6 Flash is Google's model, released Jul 21, 2026. It's ranked in 3 categories and does best at text: #29 of 416, with a ToolsGuide Score of 537 against a median of 235.

It also ranks #28 of 167 for vision (538), #56 of 147 for coding (363).

Its text and vision score uses votes only, because it has published fewer than two of the tests used for those categories.

It costs $1.50 per million input tokens and $7.50 per million output tokens, about 3.4× the median text model ($0.43).

It has published results on 7 tests and has the top score on 1 of them, including MLE-Bench.

Specifications

Creator
Google
Licence
Proprietary
Released
Jul 21, 2026
Context window
1M tokens
Input price
$1.50 / 1M
Output price
$7.50 / 1M
Tests reported
7
Settings ranked
gemini-3.6-flash-high, Gemini 3.6 Flash (High)

Model comparison

Against the ten best text models.

Text score

ToolsGuide Score out of 1,000 · Higher is better

Vision score

ToolsGuide Score out of 1,000 · Higher is better

Input price

USD per 1M input tokens · Lower is better

Leaderboards

Where Gemini 3.6 Flash sits among the top 20 in each category.

Text

#29 of 416 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full text leaderboard →

Vision

#28 of 167 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full vision leaderboard →

Coding

#56 of 147 · ToolsGuide Score out of 1,000, where 1,000 is a flawless model

Full coding leaderboard →

By task

Scored from votes on each kind of prompt alone, on the same 1,000-point scale.

Score against price

Text · the 10 priced models ranked closest · up and to the left is better value

Against its nearest rivals

Text prompts by kind · ToolsGuide Score from votes · hover for values

Text

gemini-3.6-flash-high · hover a bar for its rank

Vision

Gemini 3.6 Flash (High) · hover a bar for its rank

Coding

Gemini 3.6 Flash (High) · hover a bar for its rank

Test results

Every test Gemini 3.6 Flash has a published result on, out of 100%, with its rank among the models that took it.

  • SWE-Bench Pro

    #23 / 61

    Harder, longer software engineering tasks from real codebases.

    58.7%

    Self-reported · In the coding score

  • CharXiv-R

    #8 / 60

    Reading and reasoning about charts from scientific papers.

    89.4%

    Self-reported

  • DeepSWE 1.1

    #43 / 50

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

    49.0%

    Self-reported · In the coding score

  • Terminal-Bench 2.1

    #24 / 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.

    78.0%

    Self-reported

  • MRCR v2 (8-needle)

    #10 / 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.

    54.0%

    Self-reported · In the text score

  • OSWorld-Verified

    #5 / 28

    OSWorld-Verified is a verified subset of OSWorld, a scalable real computer environment for multimodal agents supporting task setup, execution-based evaluation, and interactive learning across Ubuntu, Windows, and macOS.

    83.0%

    Self-reported

  • MLE-Bench

    #1 / 2

    MLE-Bench evaluates AI agents on machine learning engineering tasks by measuring their performance on Kaggle competitions.

    63.9%

    Unverified