OpenAI
GPT-5 (high)
GPT-5 (high) is an OpenAI GPT-5 family model, positioned around stronger reasoning, coding, factuality, and agentic work than earlier GPT generations. This profile keeps the release context separate from the local Artificial Analysis measurements so you can compare the specific reasoning tier on benchmark quality, speed, and cost.
Introducing GPT-5Operational Metrics
Output Speed84.2 tok/s
First Token84.98s
Blended Price$3.44/M
Model Metadata
Queryable facts extracted from the upstream model payload.
ReleaseAug 7, 2025
Context Windown/a
Modalitiesn/a
Strength: MATH-500
Rank #1 across 201 models.
99.4%
Strength: AIME
Rank #1 across 194 models.
95.7%
Strength: MMLU-Pro
Rank #12 across 345 models.
87.1%
Watch Area: TTFT
Rank #288 across 293 models.
84.98s
Watch Area: Output $
Rank #263 across 325 models.
$10.00/M
Watch Area: Blended $
Rank #253 across 325 models.
$3.44/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 44.6 | #43 |
| Artificial Analysis Coding Index | coding | 36.0 | #74 |
| Artificial Analysis Math Index | math | 94.3 | #12 |
| MMLU-Pro | reasoning | 87.1% | #12 |