Capability
61.8/100
field median 58.1
#60 of 232 ranked models
GPT-5.4 Pro
Released Mar 5, 2026 — see all recent releases
Decision reading
GPT-5.4 Pro scores 61.8 out of 100 and ranks #60 of 232. This profile shows 10 source-displayable benchmark rows; its strongest eligible category is Agentic at #33. API pricing is $30 input and $180 output per million tokens.
Data as of September 4, 2026 · How the score is built
Share or export
Strongest published evidence
Agentic ranks #33. Particularly useful for coding agents, browser research, and computer-use workflows.
Validate before choosing
10 published rows leave some tracked benchmark slots empty. Knowledge is its lowest eligible category at #39.
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Price
$30input / $180 output
input median $1
blended $105
Speed
74tok/s
field median 92 tok/s
First token 151.79 s
Context
1.05Mtokens
field median 256,000
Maximum output length is tracked separately
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
GPT-5.4 Pro category percentile values
- Agentic79th percentile
- CodingNot eligible
- ReasoningNot eligible
- Knowledge79th percentile
- MathNot eligible
- MultilingualNot eligible
- MultimodalNot eligible
- Instruction followingNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#33/151
- CodingNot ranked
- ReasoningNot ranked
- Knowledge#39/181
- MathNot ranked
- MultilingualNot ranked
- MultimodalNot ranked
- Inst. FollowingNot ranked
Top decileTop quartileMid-fieldNot eligible
What it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Current modelGPT-5.4 Pro · 61.8 score · $105 blended per million tokens
Horizontal: blended price per million tokens, log scale · Vertical: public score
How much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic1/1 verified
- CodingNot measured
- Reasoning1/1 verified
- Knowledge3/4 verified
- Math3/4 verified
- MultilingualNot measured
- MultimodalNot measured
- Inst. FollowingNot measured
Verified sourceProvisionalNot measured
Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- gpt-5.4-proOpenAI GPT-5.4 Pro model documentation
- Context window
- 1.05MOpenAI GPT-5.4 Pro model documentation
- Maximum output
- Not sourced yet
- Knowledge cutoff
- Not sourced yet
- Input modalities
- text, imageOpenAI model catalog
- Output modalities
- textOpenAI model catalog
- Parameters
- Not disclosed by the provider
- Availability
- OpenAI Responses APIOpenAI model catalog
- Cloud regions
- Not tracked yet
- Lifecycle
- activeOpenAI GPT-5.4 Pro model documentation
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Not documented in the pricing recordOpenAI pricing
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #33 of 151Percentile 79thWeight 22%1 benchmarkVerified | 58.1 | #33 of 151 | 79th | 22% | 1 benchmark | Verified |
| CodingWeight 20%0 benchmarksNot measured | Not measured | Not ranked | Not available | 20% | 0 benchmarks | Not measured |
| ReasoningRank Not rankedWeight 17%1 benchmarkVerified | 70.1 | Not ranked | Not available | 17% | 1 benchmark | Verified |
| KnowledgeRank #39 of 181Percentile 79thWeight 12%4 benchmarksMixed sources | 60.7 | #39 of 181 | 79th | 12% | 4 benchmarks | Mixed sources |
| MathRank Not rankedWeight 5%4 benchmarksMixed sources | 69.0 | Not ranked | Not available | 5% | 4 benchmarks | Mixed sources |
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | Not ranked | Not available | 7% | 0 benchmarks | Not measured |
| MultimodalWeight 12%0 benchmarksNot measured | Not measured | Not ranked | Not available | 12% | 0 benchmarks | Not measured |
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | Not ranked | Not available | 5% | 0 benchmarks | Not measured |
Benchmark ledger
Agentic opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Agentic1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| BrowseComp | Score89.3% | Versus best verified row Best verified: GPT-5.6 Sol · 92.2% | Gap2.9 behind | WeightWeighted 25% | Provider exact |
Reasoning1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2 | Score83.3% | Versus best verified row Best verified: GPT-6 Astra · 95% | Gap11.7 behind | WeightWeighted 25% | Provider exact |
Knowledge4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score58.7% | Versus best verified row Best verified: Claude Fable 5.1 · 65% | Gap6.3 behind | WeightWeighted 35% | Provider exact |
| HLE w/o toolsHumanity's Last Exam without tools | Score42.7% | Versus best verified row Best verified: Claude Fable 5.1 · 60.9% | Gap18.2 behind | WeightWeighted 10% | Provider exact |
| FrontierScience | Score36.7% | Versus best verified row Best verified: GPT-5.4 Pro · 36.7% | GapBest verified | WeightDisplay only | Provider exact |
| FrontierScience Research | Score36.7% | Versus best verified row Best verified: Apodex 1.1 · 63.3% | Gap26.6 behind | WeightDisplay only | Secondary exact |
Math4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3 | Score50.000% | Versus best verified row Best verified: GPT-5.6 Sol · 89.000% | Gap39 behind | WeightWeighted 30% | Benchmark exact |
| FrontierMath v2 (Tier 4)FrontierMath v2 Tier 4 | Score37.500% | Versus best verified row Best verified: GPT-6 Astra · 97.600% | Gap60.1 behind | WeightWeighted 10% | Benchmark exact |
| IPhO 2025 (Theory)International Physics Olympiad 2025 (Theory) | Score93.5% | Versus best verified row | GapNo verified comparator | WeightDisplay only | Secondary exact |
| FrontierMath (legacy)FrontierMath legacy aggregate | Score50% | Versus best verified row Best verified: GPT-5.6 Sol · 89% | Gap39 behind | WeightDisplay only | Provider exact |
Lineage
The sequence follows explicit supersedes links. A successor's displayed score stays at least 0.1 points above its predecessor; raw benchmark rows do not move. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
Mar 5, 2026 · you are here
GPT-5.4 ProScore 61.8 · $30 / $180
Pro
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
GPT-5.4 Pro ranks #60 of 232 on the public leaderboard with a score of 61.75/100. It does not yet have enough sourced coverage for a verified position.
GPT-5.4 Pro is a proprietary model with a 1.05M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
GPT-5.4 Pro sits in the GPT-5.4 family with GPT-5.4, GPT-5.4 mini, GPT-5.4 nano. 10 of 422 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Agentic at #33, while its lowest eligible position is Knowledge at #39. particularly useful for coding agents, browser research, and computer-use workflows.
Radar
Full release historyGPT-5.4 Pro release history
GPT-5.4 and GPT-5.4 Pro released
OpenAI · Model release
Source confirmed
Radar confirmed these at the source. Already tracking GPT-5.4 Pro? See the free Radar Brief for what changes next.
Frequently asked questions
How does GPT-5.4 Pro perform overall in AI benchmarks?
GPT-5.4 Pro ranks #60 out of 232 models on the public BenchAlign leaderboard, with a score of 61.75/100. Its evidence status is Estimated, and this profile shows 10 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is GPT-5.4 Pro good for knowledge and understanding?
GPT-5.4 Pro ranks #39 out of 181 eligible models for knowledge and understanding, with a public category score of 60.7/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GPT-5.4 Pro good for mathematics?
GPT-5.4 Pro has source-displayable benchmark coverage for mathematics, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is GPT-5.4 Pro good for reasoning and logic?
GPT-5.4 Pro has source-displayable benchmark coverage for reasoning and logic, but the public category table does not assign it a rank there. The individual rows remain available for inspection. A missing category position means the evidence threshold was not met; it does not convert the model's unmeasured work into a zero.
Is GPT-5.4 Pro good for agentic tool use and computer tasks?
GPT-5.4 Pro ranks #33 out of 151 eligible models for agentic tool use and computer tasks, with a public category score of 58.1/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Which sibling models are related to GPT-5.4 Pro?
GPT-5.4 Pro belongs to the GPT-5.4 family. Related tracked variants include GPT-5.4, GPT-5.4 mini, GPT-5.4 nano. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does GPT-5.4 Pro have full benchmark coverage on BenchLM?
No. GPT-5.4 Pro currently has 11 source-displayable rows across 422 tracked benchmark slots. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of GPT-5.4 Pro?
GPT-5.4 Pro has a documented context window of 1.05M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.
Compare GPT-5.4 Pro with every tracked model410 comparisons
Last updated September 4, 2026. Runtime fields remain blank until a sourced snapshot exists.
Watch GPT-5.4 Pro in the weekly brief
Get one weekly email when material rank, price, availability, or benchmark evidence changes are worth revisiting.
Read a sample issueJoin 2,000+ readers.