Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
GPT-5 mini
Closed
Share
Add to comparison
Tool use · Reasoning
Overview
Pricing
Evaluations
Evaluation overview
Overall rank
#85
68.2 points · 180 models
Coding rank
#60
72.9 points · 160 models
Data coverage
42 items
4 sources · updated through 2026-07-16
Domain performance
Coding
#60 / 160
72.9
Research
#81 / 174
78.9
Agents
#68 / 125
67.2
Vision
#50 / 65
72.5
Long context
#52 / 82
70.1
Evaluation highlights
All evaluations
Aider Polyglot
Coding · OpenAI GPT-5 Developer Release
71.6%
3
/ 29
HMMT 2025
Reasoning · OpenAI GPT-5 Developer Release
87.8%
2
/ 16
OpenAI MRCR 2-needle 128k
Long context · OpenAI GPT-5 Developer Release
84.3%
2
/ 13
TAU2-Retail
Agents · OpenAI GPT-5 Developer Release
78.3%
4
/ 18
MMMU
Multimodal · OpenAI GPT-5 Developer Release
81.6%
11
/ 25
Internal API instruction following (hard)
Instruction following · OpenAI GPT-5 Developer Release
65.8%
1
/ 13
Basic information
Context (input / output)
400K / 128K
Release date
2025-08
Input modalities
Text · Image
Output modalities
Text
Availability
OpenAI
Full pricing
Input
$0.25 /1M
Output
$2 /1M
Related links
Official site
Version relationships
GPT-5 family
GPT-5
2025-08 · Same series
GPT-5 mini
Current
2025-08 · Current model
GPT-5 nano
2025-08 · Same series
GPT-5 Pro
2025-10 · Same series
Runtime modes
High