OpenAIo3Arena #29Apr 16, 2025

o3

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instruction-following. Use it to think through multi-step problems that involve analysis across text, code, and images.

Context Window
200K
tokens
Max Output
100K
tokens
Released
Apr 16, 2025
Arena Rank
#29
of 305 models
Output Speed
118
tokens/sec
Time to First Token
18.2s
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
structured_outputs
Tool Choice
Control tool usage
Tool Calling
Function calling support

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
Requesty$1.00$4.00$0.25
OpenRouter$2.00$8.00$0.50
Vercel AI$2.00$8.00
Martian$2.00$8.00$0.50

Benchmarks

Artificial Analysis
Intelligence IndexArtificial Analysis
78/100
Coding IndexArtificial Analysis
72/100
Math IndexArtificial Analysis
96/100
MMLU-PROArtificial Analysis
0.818/1
GPQA DiamondArtificial Analysis
0.838/1
MATH-500Artificial Analysis
0.978/1
AIME 2024Artificial Analysis
0.917/1
Humanity's Last ExamArtificial Analysis
0.208/1
LiveCodeBenchArtificial Analysis
0.772/1
SciCodeArtificial Analysis
0.462/1
Aider Polyglot
Aider PolyglotAider Polyglot
40.9/100

Model IDs

Requestyopenai/o3:flex
OpenRouteropenai/o3

Tags

visionreasoningtool-callingcaching
Compare with another model

Related Models