Skip to main content

Gemini 2.5 Flash Preview (Reasoning)

GoogleGeminiProprietary

Description

A thinking model designed for a balance between price and performance. It builds upon Gemini 2.0 Flash with upgraded reasoning, hybrid thinking control, multimodal capabilities (text, image, video, audio input), and a 1M token input context window.

Release Date
2025-04-17
Parameters
—
Context Length
1.0M
Modalities
audio, image, pdf, text, video

Capability Radar

60
general
60
coding
60
reasoning
68
scienceest.
60
agents
80
multimodal

Science is estimated from LLM Stats science scores or reasoning when no dedicated science benchmarks are available.

Rankings

No ranking data available

Benchmark Scores (LLM Stats)

(LLM Stats (zeroeval))

Factuality

SimpleQA26.9%SR

General

Global-MMLU-Lite88.4%SR
Aider-Polyglot61.9%SR
Aider-Polyglot Edit56.7%SR

Long Context

MRCR32.0%SR

Math

AIME 202488.0%SR
AIME 202572.0%SR

Multimodal

MMMU79.7%SR
Vibe-Eval65.4%SR

Reasoning

FACTS Grounding85.3%SR
GPQANYU + Cohere + Anthropic (2023)82.8%SR
LiveCodeBench v563.9%SR
SWE-Bench Verified60.4%SR
Humanity's Last Exam11.0%SR

AA Evaluation Indices

(Artificial Analysis)

No AA evaluation data available

LLM Stats Category Scores

(LLM Stats (zeroeval))
Language
90
Grounding
90
Physics
80
Healthcare
80
Biology
80
Chemistry
80
Multimodal
70
Math
60
Reasoning
60
Factuality
60
Frontend Development
60
General
60
Code
60
Vision
50
Long Context
20

Pricing

Input Price$0.3 / 1M tokens
Output Price$2.5 / 1M tokens
Blended Price (3:1)$0.85 / 1M tokens
Cache Read Price$0.03 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

2 providers

Cheapest: GoogleMost Expensive: DeepInfra
ProviderInputOutput
1GooglePRIMARY
$0.3
$2.5
2DeepInfra
$0.3
$2.5

Compare pricing across different API providers for this model.

External Sources