跳轉到主要內容

Gemini 2.5 Pro

GoogleGeminiProprietary

描述

A highly capable AI model from Google, designed for the agentic era. Gemini 2.5 Pro performs well on common benchmarks with enhanced reasoning, multimodal capabilities (text, image, video, audio input), and a 1M token context window.

發布日期
2025-06-05
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

43
general
51
coding
89
reasoning
57
science
78
agents
84
multimodal

排行榜排名

領域#排名分數來源
音訊能力63
53.0
AA
程式碼能力榜179
58.0
AA
通用能力榜198
56.0
AA
多模態榜34
54.0
LS
科學能力119
66.0
AA

基準測試分數 (LLM Stats)

(LLM Stats (zeroeval))

Biology

GPQANYU + Cohere + Anthropic (2023)86.4%自報

Code

Aider-Polyglot82.2%自報
Aider-Polyglot Edit72.7%自報
LiveCodeBench69.0%自報
SWE-Bench Verified67.2%自報

Factuality

FACTS Grounding87.8%自報
SimpleQA54.0%自報

General

MRCR93.0%自報
Global-MMLU-Lite89.2%自報
MRCR 1M (pointwise)82.9%自報
MMMU82.0%自報
LiveCodeBench v575.6%自報
Vibe-Eval67.2%自報
MRCR v2 (8-needle)16.4%自報

Healthcare

VideoMMMU83.6%自報

Math

AIME 202492.0%自報
AIME 202588.0%自報
Humanity's Last Exam21.6%自報

Multimodal

Video-MME84.8%自報

Reasoning

ARC-AGI v24.9%

AA 評測指數

(Artificial Analysis)
Math Index(Artificial Analysis)
87.7
Coding Index(Artificial Analysis)
33.3
Intelligence Index(Artificial Analysis)
25.9
Math 500(OpenAI (2024), subset of Hendrycks et al. MATH (2021))
1.0
Aime(MAA (Mathematical Association of America))
0.9
Aime 25(MAA (Mathematical Association of America))
0.9
Mmlu Pro(TIGER-Lab (Univ. of Waterloo, Toronto, CMU, 2024))
0.9
Gpqa(NYU + Cohere + Anthropic (2023))
0.8
Livecodebench(UC Berkeley + MIT + Cornell (2024))
0.8
Lcr(Artificial Analysis)
0.7
Tau2(Sierra + U Toronto + Vector Institute (2025))
0.5
Ifbench(Google Research (2023))
0.5
Scicode(UIUC + Argonne National Lab (2024))
0.4
Terminalbench V2 1
0.3
Terminalbench Hard(Stanford × Laude Institute (2026))
0.3
Hle(Center for AI Safety + Scale AI (2025))
0.2
Tau Banking
0.1

LLM Stats 分類評分

(LLM Stats (zeroeval))
Long Context
90
Language
90
Multimodal
80
Physics
80
Healthcare
80
Biology
80
Chemistry
80
Reasoning
70
General
70
Code
70
Math
60
Frontend Development
60
Factuality
50
Vision
50
Spatial Reasoning
0

定價

輸入價格$1.25 / 1M tokens
輸出價格$10 / 1M tokens
混合價格(3:1)$3.438 / 1M tokens
快取讀取價格$0.125 / 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

供應商價格排行

26 個供應商

最便宜: Google最貴: OrcaRouter
供應商輸入輸出
1Google最便宜
$0
$0.00001
2Poe
$0.87
$7
3Jiekou.AI
$1.125
$9
4302.AI
$1.25
$10
5NanoGPT
$1.25
$10
6Abacus
$1.25
$10
7Perplexity Agent
$1.25
$10
8OpenRouter
$1.25
$10
9ZenMux
$1.25
$10
10Kilo Gateway
$1.25
$10
11SAP AI Core
$1.25
$10
12Helicone
$1.25
$10
13FrogBot
$1.25
$10
14AIHubMix
$1.25
$10
15Vercel AI Gateway
$1.25
$10
16LLM Gateway
$1.25
$10
17Vertex
$1.25
$10
18FastRouter
$1.25
$10
19Auriko
$1.25
$10
20NEAR AI Cloud
$1.25
$10
21Merge Gateway
$1.25
$10
22Ofox
$1.25
$10
23Modelis
$1.25
$10
24Impossibl
$1.25
$10
25Cortecs
$1.495
$9.964
26OrcaRouter
$2.5
$15

比較該模型在不同 API 供應商之間的定價。

外部連結