GPT-5.4 Pro
OpenAI · Proprietary · rank 60 · bench-align-v5
Capability shape
Seven axes from the ranking source. A missing axis is drawn as a gap.
Runtime service evidence
Measured values with the date they were observed. Nothing is inferred from a sibling model or a provider claim.
Time to first token: latency to the first answer chunk (Artificial Analysis, via BenchLM). Reasoning models include thinking time, so values can run to tens or hundreds of seconds.
Evidence key: Observed
| Measurement | Value | Observed | Last good | Evidence |
|---|---|---|---|---|
| Time to first token | 151.79 s | 2026-09-17 | 2026-09-17 | |
| Throughput | 74 tok/s | 2026-09-17 | 2026-09-17 |
Regional or per-endpoint measurements appear only when the API supplies them; none are modelled here.
Endpoint and price matrix
Every published price component, including cache reads and writes.
| Component | USD | Evidence |
|---|---|---|
| Input / 1M tokens | $30.00 | |
| Output / 1M tokens | $180.00 | |
| Cache read / 1M tokens | Unavailable | |
| Cache write / 1M tokens | Unavailable | |
| Blended / 1M (75% input / 25% output) | $67.50 |
Workload-aware monthly cost example
10 conversations per day × 8 messages × 22 active days, 1200 input and 400 output tokens per message, no cache. This uses the same calculator as the cost simulator, so an unavailable applicable rate makes the example unavailable too.
Benchmark record
11 matched benchmark rows with their published value, unit, and provenance.
Knowledge
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| HLE Humanity's Last Exam | 58.7 | Expert-level questions | Frontier expert level | Humanity's Last Exam |
| FrontierScience FrontierScience | 36.7 | Research-level science tasks | Research frontier | FrontierScience |
| FrontierScience Research FrontierScience Research | 36.7 | Scientific research problems | Frontier scientific research | Muse Spark Eval Methodology |
| HLE w/o tools Humanity's Last Exam without tools | 42.7 | Expert-level questions | Frontier expert level | Introducing GPT-5.4 mini and nano |
Mathematics
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| IPhO 2025 (Theory) International Physics Olympiad 2025 (Theory) | 93.5 | 3 olympiad theory problems | International olympiad physics | Muse Spark Eval Methodology |
| FrontierMath (legacy) FrontierMath legacy aggregate | 50 | Historical aggregate | Research-level mathematics | FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AI |
| FrontierMath v2 (Tiers 1-3) FrontierMath v2 Tiers 1-3 | 50.000 | 295 private advanced mathematics problems | From olympiad-plus to early research mathematics | FrontierMath v2 benchmark hub |
| FrontierMath v2 (Tier 4) FrontierMath v2 Tier 4 | 37.500 | 43 private extreme-difficulty mathematics problems | Research-level mathematics requiring hours or days of expert work | FrontierMath Tier 4 v2 leaderboard |
Reasoning
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| ARC-AGI-2 Abstraction and Reasoning Corpus for AGI v2 | 83.3 | Visual pattern completion and abstract reasoning | Expert-level — hardest public reasoning benchmark | ARC-AGI-2: A Harder General Intelligence Benchmark |
| CritPt Critical Physics Tasks | 30.0 | Research-level physics questions | Research-level physics reasoning | CritPt Benchmark Leaderboard |
Agentic
| Benchmark | Value | Tasks | Difficulty | Provenance |
|---|---|---|---|---|
| BrowseComp BrowseComp | 89.3 | Research questions requiring browsing | Hard web research | BrowseComp |
Lifecycle and limitations log
Lifecycle events the source associates with this model, plus what this profile does not claim.
That is not evidence the model has no lifecycle plan — only that this source published none.