Google
Google

Gemini 2.5 Pro

Model ID:gemini-2.5-pro
2025-06-17Proprietary Model
API
OverallNo.23
PopularityNo.32

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy and nuanced context handling. Gemini 2.5 Pro achieves top-tier performance on multiple benchmarks, including first-place positioning on the LMArena leaderboard, reflecting superior human-preference alignment and complex problem-solving abilities.

Knowledge Cutoff
2025-01-31

The date this AI finished learning. It may not know about things that happened after this date.

Input → Output Format

The types of content this AI can receive, and what it can produce in return.

Context Memory
1.0MIN66KOUT

The maximum amount of text the AI can read and process in a single request. A larger number means it can handle longer documents or conversations.

Cost/1M Words
$1.25IN$10OUT

The cost of using this AI directly in your own application. Shown in USD per 1 million units of text (tokens).

AI Performance Evaluation

Arena Overall Score
1448
±3
As of 2026-04-02
Overall Rank
No.32
105,868 Votes
Arena by Ability
Hard Prompts
1461±4No.40
Expert Knowledge
1465±8No.34
Instruction Following
1443±4No.26
Conversation Memory
1451±5No.33
Creative
1449±6No.14
Coding
1467±5No.58
Math
1444±8No.30
Arena by Occupation
Creative Writing
1449±5No.17
Social Sciences
1474±5No.24
Media
1434±5No.21
Business
1436±5No.44
Healthcare
1469±8No.33
Legal
1466±8No.23
Software
1463±4No.48
Mathematics
1450±8No.30
Reasoning Ability
AA Intelligence Index
35%↓4%
MMLU-Pro
86%↑4%
GPQA Diamond
84%↑2%
HLE
21%↑4%
Math
AA Math Index
88%↑13%
MATH-500
97%↑3%
AIME 2024
89%↑29%
AIME 2025
88%↑13%
Coding Ability
AA Coding Index
32%↓5%
LiveCodeBench
80%↑15%
SciCode
43%↑1%
TerminalBench
27%↓8%
Instruction Following
IFBench
49%↓9%
환각률 (HHEM)
7.0%↓4%
사실 일관성 (HHEM)
93%↑4%
Long Context
AA-LCR
66%↑2%
Agentic AI Ability
TAU2
54%↓17%
Speed
Standard Mode
133tok/sec↑55
First Output 21.21s
Artificial Analysis