o3-mini
OpenAIOpenAI o-seriesProprietary
Description
A smaller variant of O3, expected to offer enhanced multimodal capabilities, improved reasoning, and more efficient resource utilization compared to previous models while maintaining strong performance on core tasks.
Release Date
2025-01-31
Parameters
—
Context Length
200K
Modalities
text
Capability Radar
35
general
65
coding
83
reasoning
49
scienceest.
40
agents
0
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 217 | 45.0 | AA |
| General Ranking | 234 | 45.0 | AA |
| Math Reasoning | 50 | 89.0 | AA |
| Reasoning | 83 | 54.0 | LS |
| Science | 168 | 52.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
77.2%SR
Code
Aider-Polyglot
66.7%SR
Aider-Polyglot Edit
60.4%SR
SWE-Bench Verified
49.3%SR
SWE-Lancer
18.0%SR
SWE-Lancer (IC-Diamond subset)
7.4%SR
Communication
Multi-IF
79.5%SR
TAU-bench Retail
57.6%SR
Multi-Challenge
39.9%SR
TAU-bench Airline
32.4%SR
Factuality
SimpleQA
15.0%SR
Finance
MMLU
86.9%SR
General
IFEval
93.9%SR
LiveBench
84.6%SR
Multilingual MMLU
80.7%SR
Internal API instruction following (hard)
50.0%SR
Language
COLLIE
98.7%SR
Long Context
OpenAI-MRCR: 2 needle 128k
18.7%SR
ComplexFuncBench
17.6%SR
Math
MATH
97.9%SR
MGSM
92.0%SR
AIME 2024
87.3%SR
FrontierMath
9.2%SR
Reasoning
Graphwalks parents <128k
58.3%SR
Graphwalks BFS <128k
51.0%SR
AA Evaluation Indices
Intelligence Index19.0
Math 5001.0
Mmlu Pro0.8
Aime0.8
Gpqa0.7
Livecodebench0.7
Scicode0.4
Tau20.3
Hle0.1
Terminalbench Hard0.1
LLM Stats Category Scores
Writing100
Instruction Following90
Language90
Legal90
Finance90
Healthcare90
Math80
Physics80
Biology80
Chemistry80
General70
Reasoning60
Structured Output60
Spatial Reasoning50
Frontend Development50
Communication50
Code40
Tool Calling40
Long Context20
Factuality10
Pricing
Input Price$1.1 / 1M tokens
Output Price$4.4 / 1M tokens
Blended Price (3:1)$1.925 / 1M tokens
Cache Read Price$0.55 / 1M tokens
Speed
Tokens/sec229.8
Time to First Token5.43s
Time to Answer5.43s
Provider Price Ranking
Provider Price Ranking
9 providers
Cheapest: NanoGPTMost Expensive: Azure
ProviderInputOutput
1NanoGPTCheapest
$1.088
$4.3996
2OpenAIPRIMARY
$1.1
$4.4
3Abacus
$1.1
$4.4
4Jiekou.AI
$1.1
$4.4
5Helicone
$1.1
$4.4
6Azure Cognitive Services
$1.1
$4.4
7DigitalOcean
$1.1
$4.4
8LLM Gateway
$1.1
$4.4
9Azure
$1.1
$4.4
Compare pricing across different API providers for this model.