GPT-5 mini (high)
OpenAIGPTProprietary
Description
A faster, more cost-efficient version of GPT-5 for well-defined tasks. Great for well-defined tasks and precise prompts with high reasoning capabilities at reduced cost.
Release Date
2025-08-07
Parameters
—
Context Length
400K
Modalities
file, image, text
Capability Radar
51
general
53
coding
89
reasoning
55
scienceest.
0
agents
85
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 54 | 71.0 | AA |
| General Ranking | 60 | 77.0 | AA |
| Math Reasoning | 30 | 92.0 | AA |
| Science | 75 | 66.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
82.3%SR
Math
AIME 2025
91.1%SR
HMMT 2025
87.8%SR
FrontierMath
22.1%SR
Humanity's Last Exam
16.7%SR
AA Evaluation Indices
Math Index90.7
Intelligence Index41.2
Coding Index35.3
Aime 250.9
Livecodebench0.8
Mmlu Pro0.8
Gpqa0.8
Ifbench0.8
Tau20.7
Lcr0.7
Scicode0.4
Terminalbench Hard0.3
Hle0.2
LLM Stats Category Scores
Biology80
Chemistry80
General80
Physics80
Math50
Reasoning50
Vision20
Pricing
Input Price$0.25 / 1M tokens
Output Price$2 / 1M tokens
Blended Price (3:1)$0.688 / 1M tokens
Speed
Tokens/sec71.4 tokens/s
Time to First Token95.73s
Time to Answer95.73s
Available Providers
(LS internal units)| Provider | Input Price | Output Price |
|---|---|---|
| OpenAI | 250K | 2.0M |