跳轉到主要內容

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

36
general
47
coding
86
reasoning
46
science
74
agents
80
multimodal

排行榜排名

領域#排名分數來源
程式碼能力榜189
55.0
AA
通用能力榜265
47.0
AA
科學能力240
50.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)82.8%自報

Code

Aider-Polyglot61.9%自報
SWE-Bench Verified60.4%自報
Aider-Polyglot Edit56.7%自報

Factuality

FACTS Grounding85.3%自報
SimpleQA26.9%自報

General

Global-MMLU-Lite88.4%自報
MMMU79.7%自報
Vibe-Eval65.4%自報
LiveCodeBench v563.9%自報
MRCR32.0%自報

Math

AIME 202488.0%自報
AIME 202572.0%自報
Humanity's Last Exam11.0%自報

AA 評測指數

(Artificial Analysis)
Intelligence Index(Artificial Analysis)
17.7
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
1.0
Aime(MAA (Mathematical Association of America))
0.8
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.8
Gpqa(NYU + Cohere + Anthropic (2023))
0.7
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.5
Scicode(UIUC + Argonne National Lab (2024))
0.4
Hle(Center for AI Safety + Scale AI (2025))
0.1

LLM Stats 分類評分

(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

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

暫無提供商資料

外部連結