Skip to content

OpenAI Proprietary Released Aug 7, 2025 Updated

GPT-5 mini

ToolsGuide Scores, rankings, test results and price.

Model summary

  • Text #153 / 416

    301 / 1,000

    ToolsGuide Score· votes 276, tests 331

  • Vision #100 / 167

    300 / 1,000

    ToolsGuide Score· votes only

  • Price per 1M tokens

    In $0.25· Out $2.00

    $0.25

    Input · median text model $0.43

Summary

GPT-5 mini is OpenAI's model, released Aug 7, 2025. It's ranked in 2 categories and does best at text: #153 of 416, with a ToolsGuide Score of 301 against a median of 235.

It also ranks #100 of 167 for vision (300).

Its vision score uses votes only, because it has published fewer than two of the tests used for that category.

It costs $0.25 per million input tokens and $2.00 per million output tokens, below the median text model ($0.43).

It has published results on 5 tests.

Specifications

Creator
OpenAI
Licence
Proprietary
Released
Aug 7, 2025
Context window
400K tokens
Input price
$0.25 / 1M
Output price
$2.00 / 1M
Tests reported
5
Settings ranked
gpt-5-mini-high, GPT-5 mini (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 GPT-5 mini sits among the top 20 in each category.

Text

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

Full text leaderboard →

Vision

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

Full vision 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

gpt-5-mini-high · hover a bar for its rank

Vision

GPT-5 mini (High) · hover a bar for its rank

Test results

Every test GPT-5 mini has a published result on, out of 100%, with its rank among the models that took it.

  • GPQA

    #89 / 256

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

    82.3%

    Self-reported

  • AIME 2025

    #44 / 123

    Competition maths problems from the 2025 American Invitational Mathematics Exam.

    91.1%

    Self-reported

  • Humanity's Last Exam

    #80 / 108

    Humanity's Last Exam (HLE) is a multi-modal academic benchmark with 2,500 questions across mathematics, humanities, and natural sciences, designed to test LLM capabilities at the frontier of human knowledge with unambiguous, verifiable solutions

    16.7%

    Self-reported · In the text score· In the vision score

  • HMMT 2025

    #20 / 33

    Harvard-MIT Mathematics Tournament 2025 - A prestigious student-organized mathematics competition for high school students featuring two tournaments (November 2025 at MIT and February 2026 at Harvard) with individual tests, team rounds, and guts rounds

    87.8%

    Self-reported

  • FrontierMath

    #12 / 17

    A benchmark of hundreds of original, exceptionally challenging mathematics problems crafted and vetted by expert mathematicians, covering most major branches of modern mathematics from number theory and real analysis to algebraic geometry and category theory.

    22.1%

    Self-reported