CorX Labs

Gemini 2.5 Flash

by Google DeepMind · United States
ProprietaryReasoningVisionTool calling1M context

A thinking model with a budget dial you set per request — including zero.


Specification

The numbers

Maker
Google DeepMind
Released
2025-04
Parameters
Not reported
Architecture
Not reported
Context window
1,048,576 tokens
Max output
65,536 tokens
Input
Text, Image, Audio, Video
Output
Text
Reasoning
Yes
Tool calling
Yes
Knowledge cutoff
2025-01
Licence
Proprietary
Availability
Not reported
Weights
Not released

Cost

Price per million tokens

Input
$0.30 / M tokens
Output
$2.50 / M tokens
Cached input
$0.075
Blended 3:1
$0.85

Standard first-party API rate, excluding batch discounts. Reasoning models bill thinking tokens as output, so cost per answer can far exceed the cost per token suggests.

Published scores

Benchmarks

Figures published by Google DeepMind or taken from a public leaderboard. Row last checked 2026-08.

Gemini 2.5 Flash by capability category, with its rank among models reporting the same tests.
CategoryScore Rank
ReasoningGPQA Diamond78.3%20 of 83 reporting the same tests
MathsAIME 202578.0%37 of 56 reporting the same tests
CodingWriting and repairing real codeNot reported
KnowledgeBreadth of factual recall under exam conditionsNot reported
MultimodalMMMU79.7%7 of 39 reporting the same tests
Instruction followingObeying an exact, checkable formatNot reported
Human preferenceLMArena Elo13935 of 24 reporting the same tests

A category averages every benchmark in it that Gemini 2.5 Flash reports. The rank counts only models that report the same tests, so it never compares an average over three benchmarks against an average over one.

Every reported test

MMLU-ProKnowledgeNot reportedNo figure published
GPQA DiamondReasoning78.3%Rank 20 of 83 models reporting
AIME 2025Maths78%Rank 37 of 56 models reporting
MATH-500MathsNot reportedNo figure published
SWE-bench VerifiedCodingNot reportedNo figure published
SWE-bench ProCodingNot reportedNo figure published
Terminal-Bench 2.1CodingNot reportedNo figure published
Frontier-Bench v0.1ReasoningNot reportedNo figure published
Terminal-Bench 4.0CodingNot reportedNo figure published
LiveCodeBenchCodingNot reportedNo figure published
HumanEvalCodingNot reportedNo figure published
MMMUMultimodal79.7%Rank 7 of 39 models reporting
IFEvalInstruction followingNot reportedNo figure published
LMArena EloHuman preference1393Rank 5 of 24 models reporting

Where these numbers come from

Every score on this page is a published figure, taken from the model's own card, system card, technical report or release post, or from a public leaderboard. CorX Labs did not run these evaluations. Most are self-reported by the lab that built the model, which means they were produced under that lab's own choice of prompt, scaffold and number of attempts — so treat them as a starting point for a shortlist, not as a settled ranking.

A score someone other than the model's maker measured is marked Independent and names its measurer. Those are the stronger numbers on this page — an outside harness has no reason to flatter anyone — and there are not many of them.

Where a figure has not been published, the cell reads Not reported rather than an estimate. Nothing here is inferred, interpolated or guessed. Each model records the month its row was last checked. Full method and caveats.

Same maker

Other models from Google DeepMind

AI models with context window, price per million tokens and published benchmark scores. Sortable by any column.
Gemini 3 ProGoogle DeepMindGoogle DeepMind1M$2.00$12.0091.9%95%76.2%Proprietary
Gemini 2.5 Flash-LiteGoogle DeepMindGoogle DeepMind1M$0.10$0.4064.6%49.8%Proprietary
Gemini 2.5 ProGoogle DeepMindGoogle DeepMind1M$1.25$10.0084%86.7%63.8%Proprietary
Gemma 3 27BGoogle DeepMindGoogle DeepMind131K$0.10$0.2067.5%42.4%Gemma Terms of Use
Gemma 3 12BGoogle DeepMindGoogle DeepMind131K$0.05$0.1060.6%34.9%Gemma Terms of Use
Gemma 3 4BGoogle DeepMindGoogle DeepMind131K$0.02$0.0443.6%Gemma Terms of Use
Gemini 2.0 Flash-LiteGoogle DeepMindGoogle DeepMind1M$0.075$0.3071.6%51.5%Proprietary
Gemini 2.0 FlashGoogle DeepMindGoogle DeepMind1M$0.10$0.4077.6%62.1%Proprietary
Gemma 2 27BGoogle DeepMindGoogle DeepMind8.2K$0.27$0.2756%Gemma Terms of Use
Gemma 2 9BGoogle DeepMindGoogle DeepMind8.2K$0.06$0.0645%Gemma Terms of Use
Gemini 1.5 ProGoogle DeepMindGoogle DeepMind2.1M$1.25$5.0075.8%59.1%Proprietary
Gemini 1.5 FlashGoogle DeepMindGoogle DeepMind1M$0.075$0.3067.3%51%Proprietary