About o4 Mini
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...
Specifications
- Provider
- OpenAI
- Context Length
- 200,000 tokens
- Input Types
- image, text, file
- Output Types
- text
- Category
- openai/o4-mini-2025-04-16
- Added
- 4/16/2025
Benchmark Performance
How o4 Mini compares to its closest rivals across industry benchmarks
Evaluates AI ability to resolve real GitHub issues from Python repositories
Metric: % Resolved
#14
Qwen3-Coder 480B/A35B Instruct
55.4
#16
Claude 3.7 Sonnet (20250219)
52.8
#21
gpt-oss-120b
26.0
30 problems from the 2025 American Invitational Mathematics Examination testing olympiad-level math reasoning
Metric: Accuracy %
#5
Claude-Opus-4.1 (Think)
25.6
Challenging math contest benchmark featuring the most difficult olympiad-level problems
Metric: Accuracy %
#5
Claude-Opus-4.1 (Think)
25.6
Comparison with o3 Mini
| Specification | o3 Mini Previous | o4 Mini Current | Change |
|---|---|---|---|
| Context Window | 200K | 200K | |
| Reasoning Support | |||
| Input Types | text, file | image, text, file | |
| Output Types | text | text | |
| LMArena Score | 1348 | 1391 | |
| Input Price (per 1M) | $1.10 | $1.10 | |
| Output Price (per 1M) | $4.40 | $4.40 |
Frequently Asked Questions
Common questions about o4 Mini