Gemini 2.5 Pro is Google's state-of-the-art reasoning model, designed for advanced coding, mathematics, and scientific tasks that demand deep analytical thinking. It employs built-in "thinking" capabilities that enable step-by-step reasoning through complex problems with enhanced accuracy, and achieved first place on the LMArena leaderboard upon release, reflecting superior human-preference alignment. With a 1M-token context window and multimodal input support, it excels at complex problem-solving, long-document analysis, and research-grade workflows requiring the highest level of reasoning depth.
API|VisionReasoningWeb SearchFile|Proprietary Model
Knowledge Cutoff
2025-01-31
Input → Output Format
Context Memory
1.0MIN66KOUT
AI Performance Evaluation
Arena Overall Score
1448
±3As of 2026-04-23
Overall Rank
No.38
111,209 Votes
Arena by Ability
Hard Prompts
1460±3No.48
Expert Knowledge
1464±8No.43
Instruction Following
1442±4No.34
Conversation Memory
1451±5No.42
Creative
1447±6No.18
Coding
1466±5No.69
Math
1444±7No.37
Arena by Occupation
Creative Writing
1448±5No.21
Social Sciences
1473±5No.27
Media
1433±5No.25
Business
1437±5No.50
Healthcare
1468±8No.41
Legal
1467±7No.27
Software
1461±4No.60
Mathematics
1450±8No.35
Source:Arena Intelligence
Overall
AA Intelligence Index
35%↓4%
LiveBench
57%↓3%
ForecastBench
60%↑1%
Reasoning & Math
AA Math Index
88%↑14%
GPQA Diamond
84%↑3%
HLE
21%↑4%
MMLU-Pro
86%↑4%
AIME 2025
88%↑14%
MATH-500
97%↑4%
LB Reasoning
71%↑11%
LB Math
68%↓5%
LB Data
52%↑2%
Coding
AA Coding Index
32%↓2%
LiveCodeBench
80%↑15%
LB Coding
76%↑2%
LB Agentic
33%↓10%
TAU2
54%↓19%
TerminalBench
27%↓5%
SciCode
43%↑2%
Language & Instructions
IFBench
49%↓8%
AA-LCR
66%↑4%
Hallucination (HHEM)
7.0%↓3%
Factual (HHEM)
93%↑3%
LB Language
76%↑4%
LB IF
33%↓13%
Output Speed
Standard Mode
131tok/s↑49
First Output 19.49s
