Gemini 2.5 Flash Preview (Reasoning)

GoogleGeminiProprietary

描述

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.

發布日期

2025-04-17

參數規模

—

上下文長度

1.0M

支援模態

audio, image, pdf, text, video

能力雷達圖

general

coding

reasoning

science

agents

multimodal

排行榜排名

領域	#排名	分數	來源
程式碼能力榜	269	55.0	AA
通用能力榜	344	40.0	AA
多模態榜	46	58.0	LS
科學能力	325	44.0	AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Factuality

SimpleQA

26.9%自報

General

Global-MMLU-Lite

88.4%自報

Aider-Polyglot

61.9%自報

Aider-Polyglot Edit

56.7%自報

Long Context

MRCR

32.0%自報

Math

AIME 2024

88.0%自報

AIME 2025

72.0%自報

Multimodal

MMMU

79.7%自報

Vibe-Eval

65.4%自報

Reasoning

FACTS Grounding

85.3%自報

GPQANYU + Cohere + Anthropic (2023)

82.8%自報

LiveCodeBench v5

63.9%自報

SWE-Bench Verified

60.4%自報

Humanity's Last Exam

11.0%自報

AA 評測指數

(Artificial Analysis)

Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))

98.1

Aime(MAA (Mathematical Association of America))

84.3

Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))

80.0

Gpqa(NYU + Cohere + Anthropic (2023))

69.8

Livecodebench(UC Berkeley + MIT + Cornell (2024))

50.5

Hle(Center for AI Safety + Scale AI (2025))

12.1

Intelligence Index(Artificial Analysis)

11.7

LLM Stats 分類評分

(LLM Stats (zeroeval))

Language

Grounding

Physics

Healthcare

Biology

Chemistry

Multimodal

Math

Reasoning

Factuality

Frontend Development

General

Code

Vision

Long Context

定價

輸入價格免費

輸出價格免費

混合價格(3:1)免費

快取讀取價格$0.03 / 1M tokens

速度

Tokens/秒0.0

首Token延遲0.00s

首回答延遲0.00s

供應商價格排行

1 個供應商

供應商輸入輸出

1DeepInfra

比較該模型在不同 API 供應商之間的定價。

外部連結

LLM Stats Artificial Analysis