GoogleGemini 2.5Arena #16Jun 17, 2025

Gemini 2.5 Pro

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.

Context Window
1.0M
tokens
Max Output
66K
tokens
Released
Jun 17, 2025
Arena Rank
#16
of 305 models
Output Speed
195
tokens/sec
Time to First Token
1.1s
TTFT

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
Prompt Caching
🖥Computer Use
🎨Image Generation

Supported Parameters

Include Reasoning
Show reasoning tokens
Max Tokens
Output length limit
Reasoning
Extended thinking
Response Format
JSON mode / structured output
Seed
Deterministic outputs
Stop Sequences
Custom stop tokens
structured_outputs
Temperature
Controls randomness
Tool Choice
Control tool usage
Tool Calling
Function calling support
Top P
Nucleus sampling

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
Requesty$1.25$10.00$0.31
OpenRouter$1.25$10.00$0.13
Vercel AI$1.25$10.00
Martian$1.25$10.00
DeepInfra$1.25$10.00

Benchmarks

Artificial Analysis
Intelligence IndexArtificial Analysis
73/100
Coding IndexArtificial Analysis
70/100
Math IndexArtificial Analysis
92/100
MMLU-PROArtificial Analysis
0.828/1
GPQA DiamondArtificial Analysis
0.785/1
MATH-500Artificial Analysis
0.968/1
AIME 2024Artificial Analysis
0.87/1
Humanity's Last ExamArtificial Analysis
0.185/1
LiveCodeBenchArtificial Analysis
0.745/1
SciCodeArtificial Analysis
0.445/1

Model IDs

Requestygoogle/gemini-2.5-pro
OpenRoutergoogle/gemini-2.5-pro

Tags

visionreasoningtool-callingcaching

Available Regions

EUUS
Compare with another model

Related Models