o3
OpenAIOpenAI o-seriesProprietary
Description
OpenAI's most powerful reasoning model. 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.
Release Date
2025-04-16
Parameters
—
Context Length
200K
Modalities
image, pdf, text
Capability Radar
46
general
72
coding
90
reasoning
56
science
70
agents
85
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 133 | 33.0 | LS |
| Code Ranking | 71 | 77.0 | AA |
| General Ranking | 96 | 71.0 | AA |
| Multimodal Ranking | 38 | 51.0 | LS |
| Science | 140 | 63.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
Tau-bench
63.0%SR
BrowseCompOpenAI (2025)
49.7%SR
Biology
GPQANYU + Cohere + Anthropic (2023)
83.3%SR
Code
Aider-Polyglot
81.3%SR
SWE-Bench Verified
69.1%SR
Communication
Tau2 Retail
80.2%SR
Tau2 Airline
64.8%SR
Multi-Challenge
60.4%SR
Tau2 Telecom
58.2%SR
General
MMMU
82.9%SR
MMMU-Pro
76.4%SR
Healthcare
VideoMMMU
83.3%SR
Language
COLLIE
98.4%SR
Math
AIME 2024
91.6%SR
MathVista
86.8%SR
AIME 2025
86.4%SR
FrontierMath
15.8%SR
Humanity's Last Exam
14.7%SR
Multimodal
CharXiv-R
78.6%SR
Reasoning
ARC-AGI
88.0%SR
ERQA
64.0%SR
ARC-AGI v2
6.5%
AA Evaluation Indices
(Artificial Analysis)Math Index(Artificial Analysis)88.3
Intelligence Index(Artificial Analysis)31.1
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
Tau2(Sierra + U Toronto + Vector Institute (2025))0.8
Lcr(Artificial Analysis)0.7
Ifbench(Google Research (2023))0.7
Scicode(UIUC + Argonne National Lab (2024))0.4
Terminalbench Hard(Stanford × Laude Institute (2026))0.4
Hle(Center for AI Safety + Scale AI (2025))0.2
LLM Stats Category Scores
(LLM Stats (zeroeval))Language100
Writing100
Multimodal80
Physics80
Healthcare80
Biology80
Chemistry80
Code80
Reasoning70
Frontend Development70
General70
Communication70
Tool Calling70
Math60
Agents60
Vision60
Search50
Spatial Reasoning50
Pricing
Input Price$2 / 1M tokens
Output Price$8 / 1M tokens
Blended Price (3:1)$3.5 / 1M tokens
Cache Read Price$0.5 / 1M tokens
Speed
Tokens/sec106.2
Time to First Token7.90s
Time to Answer7.90s
Provider Price Ranking
Provider Price Ranking
16 providers
Cheapest: PoeMost Expensive: Jiekou.AI
ProviderInputOutput
1PoeCheapest
$1.8
$7.2
2OpenAIPRIMARY
$2
$8
3NanoGPT
$2
$8
4Abacus
$2
$8
5OpenRouter
$2
$8
6Kilo Gateway
$2
$8
7Cloudflare AI Gateway
$2
$8
8Helicone
$2
$8
9Azure Cognitive Services
$2
$8
10Vercel AI Gateway
$2
$8
11LLM Gateway
$2
$8
12Azure
$2
$8
13NEAR AI Cloud
$2
$8
14Merge Gateway
$2
$8
15Impossibl
$2
$8
16Jiekou.AI
$10
$40
Compare pricing across different API providers for this model.