WritingmateWritingmate

AI model reference · 2026

Gemini 2.5 Pro Preview 05-06

Google: Gemini 2.5 Pro Preview 05-06 logoGoogleModel details, evidence, and API facts

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.

Text generation
Image input
Reasoning
Provider endpoint accepts tool parameters
Try Gemini 2.5 Pro Preview 05-06Compare with another model
Context window
1,048,576 tokens
Maximum output
65,535 tokens
Base provider API input
$1.25 / 1M tokens
Starting provider API rate; context tiers apply
Published evidence
5 benchmarks, 0 Arena results

Overview

About Gemini 2.5 Pro Preview 05-06

A concise catalog overview. Technical limits and published evaluation evidence are listed separately below.

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.

text
multimodal
reasoning

Published evaluations

Benchmark results

Only results mapped to this exact model and backed by a named source appear here. Different evaluation protocols are not treated as interchangeable.

Source-backed benchmark results for Gemini 2.5 Pro Preview 05-06
BenchmarkScoreEvaluation detailsSource
SWE-Bench VerifiedA human-validated subset of real GitHub issues used to measure whether a coding agent can produce repository patches that resolve the associated tests.53.6%ResolvedThe published protocol is not fully disclosed.Methodology www.swebench.comLegacy leaderboard
AIME 202530 problems from the 2025 American Invitational Mathematics Examination testing olympiad-level math reasoning35.6Accuracy %The published protocol is not fully disclosed.Methodology matharena.aiLegacy leaderboard
Artificial Analysis Intelligence IndexComprehensive comparison of AI models across intelligence, price, speed, and latency60Intelligence IndexThe published protocol is not fully disclosed.Methodology artificialanalysis.aiLegacy leaderboard
MathArena ApexChallenging math contest benchmark featuring the most difficult olympiad-level problems35.6Accuracy %The published protocol is not fully disclosed.Methodology matharena.aiLegacy leaderboard
Vending-Bench 2Tests AI models ability to manage a simulated vending machine business over a year573.64Money Balance ($)The published protocol is not fully disclosed.Methodology andonlabs.comLegacy leaderboard

Human preference

Arena results

Arena scores come from blind human preference votes. They are reported separately from task benchmarks and are not used as substitutes for missing benchmark results.

No exact Arena match is available for this model. Similar names and provider variants are not merged automatically.

Technical reference

Specifications and API facts

Technical limits and reference provider prices come from the current catalog unless a reviewed external source is listed. Missing values stay marked as unavailable.

Model
Provider
Google
Release date
Not available in reviewed sources
Catalog added
May 7, 2025
Context window
1,048,576 tokens
Maximum output
65,535 tokens
Knowledge cutoff
2025-01-31
License
Not available in reviewed sources
Capabilities and API
Input types
Text, Image, File, Audio, Video
Output types
Text
Reasoning
Supported
Provider endpoint tool parameters
Accepts tool parameters
Base provider API input
$1.25 / 1M tokens
Base provider cached input
$0.125 / 1M tokens
Base provider API output
$10 / 1M tokens
Provider tier at ≥ 200,000 prompt tokens
Input $2.50 / 1M tokensOutput $15 / 1M tokensCached input $0.25 / 1M tokens

Provider token rates are context-dependent. The base rates apply below the listed prompt thresholds; the matching tier applies at or above each threshold.

These are reference provider API rates, not Writingmate checkout charges. Access in Writingmate follows the allowances of your Writingmate plan.

Provenance

Sources and update status

Source links are attached to the facts and evaluations they support. Catalog-only values are not presented as independently verified claims.

Evidence last updated Dec 28, 2025.

Catalog record updated May 7, 2025.

Catalog-added dates describe when a model entered the catalog, not necessarily its public release date.

Try Gemini 2.5 Pro Preview 05-06 in Writingmate

Use this model, then compare its response with other AI models in the same workspace.

Get startedCompare models