NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/o4 Mini
OpenAI logo

o4 Mini

by OpenAI · Released Apr 2025

Multimodal
51.4
avg score
Rank #135
Compare
Better than 57% of all models
Context
200K tokens (~100 books)
Input $/1M
$1.10
Output $/1M
$4.40
Type
multimodal
License
Proprietary
Benchmarks
33 tested
Data as of
About

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports tool use and demonstrates competitive reasoning...

Tested on 33 benchmarks · BenchGecko score 51.4. Top scores: MATH level 5 (97.8%), HELM — IFEval (92.9%), HELM — WildBench (85.4%).

Looking for similar performance at lower cost?
Gemma 2 9B scores 51.1 (99% as good) at $0.03/1M input · 97% cheaper
Capabilities
coding
47.0
#105 globally
reasoning
44.2
#93 globally
math
46.2
#134 globally
knowledge
53.9
#93 globally
general
36.6
#87 globally
language
92.9
#7 globally
Benchmark Scores
Compare All
Tested on 33 benchmarks · Ranked across 6 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
Aider polyglot

Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.

72.0·
CadEval

Computer-aided design evaluation. Tests understanding of CAD concepts, 3D modeling, and engineering design principles.

62.0·
WeirdML

Unusual and adversarial machine learning challenges. Tests robustness of reasoning about edge cases in ML systems.

52.6·
reasoningCompare reasoning →
HELM — WildBench

Stanford HELM WildBench evaluation. Tests reasoning on challenging real-world tasks.

85.4·
ARC-AGI

Abstraction and Reasoning Corpus. Tests fluid intelligence through novel visual pattern recognition puzzles. Core measure of general intelligence.

58.7·
SimpleBench

Deceptively simple questions that humans find easy but AI models often get wrong. Tests common sense and reasoning gaps.

26.4·
mathCompare math →
MATH level 5

Competition-level math from AMC, AIME, and olympiad problems. Level 5 is the hardest tier, requiring creative problem-solving.

97.8·
OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

81.7·
HELM — Omni-MATH

Stanford HELM evaluation of mathematical reasoning across diverse problem types.

72.0·
Quick compare:minimax logovs MiniMax M2.5DeepSeek logovs DeepSeek V3.2minimax logovs MiniMax M2.7
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · OpenAI o4
Apr 2025
51.4
$1.10/M in200Kctx33 benchmarks
Apr 2025
$0.55/M in(-0.55)200Kctx
Oct 2025
$2.00/M in(+1.45)200Kctx
Apr 2025
$1.10/M in(-0.90)200Kctx1 benchmark
Apr 2025
$0.55/M in(-0.55)200Kctx
See the full o4 family →
Similar Models
minimax logo
MiniMax M2.5
minimax
51.4$0.27/1M
DeepSeek logo
DeepSeek V3.2
DeepSeek
51.3$0.28/1M
minimax logo
MiniMax M2.7
minimax
51.2$0.21/1M
Links
Info
OpenAIPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@OpenAI
BenchGecko API
o4-mini
Specifications
  • Typemultimodal
  • Context200K tokens (~100 books)
  • ReleasedApr 2025
  • LicenseProprietary
  • StatusActive
  • Cost / Message~$0.007
Available On
OpenAI logoOpenAI$1.10
Categories
codingreasoningmathknowledgegenerallanguage
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
minimax logoMiniMax M2.5
51.4
DeepSeek logoDeepSeek V3.2
51.3
minimax logoMiniMax M2.7
51.2
DeepSeek logoDeepSeek V3.2 Exp
51.6
o4 Mini is a proprietary multimodal AI model by OpenAI, released in April 2025. It has an average benchmark score of 51.4. Context window: 200K tokens.

Related Models

MiniMax M2.5 · minimaxDeepSeek V3.2 · DeepSeekMiniMax M2.7 · minimaxDeepSeek V3.2 Exp · DeepSeekGemma 2 9B · Google DeepMind

Benchmarks

MATH level 5HELM — IFEvalHELM — WildBenchHELM — MMLU-ProOTIS Mock AIME 2024-2025

Related Pages

OpenAI · ProviderOpenAI · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • o4 Mini by OpenAI. BenchGecko score 51.4, rank 135 of 312 scored models (normalized average of public benchmark scores).
  • List price $1.10 input · $4.40 output per 1M tokens (as of 2026-10-05).
  • Sold by 1 provider (as of 2026-10-05): OpenAI $1.10 in / $4.40 out.

How to cite · data as of 2026-10-05

o4 Mini · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/o4-mini

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP