Data as of October 29, 2026 · How the score is built
GPT-5.4 mini
Decision readingGPT-5.4 mini scores 53 out of 100 and ranks #90 of 216. This profile shows 22 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #29. API pricing is $0.75 input and $4.5 output per million tokens, with cached input at $0.075.
Released Mar 17, 2026 — see all recent releases
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.
Capability
53/100
field median 50.5#90 of 216 ranked models
Public
#90of 216
Verified #45 of 77
Price
$0.75input / $4.50 output
input median $0.75cached $0.075 · blended $2.63
Speed
201tok/s
field median 92 tok/sFirst token 3.85 s
Context
400Ktokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Multimodal & Grounded ranks #29. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Validate before choosing
22 published rows leave some tracked benchmark slots empty. Agentic is its lowest eligible category at #84.
Source-linked · 22 displayable benchmark rows
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 #84 of 135Percentile 38thWeight 22%6 benchmarksVerified | 36.4 | 6 benchmarks | Verified | |||
| CodingRank #80 of 156Percentile 49thWeight 20%5 benchmarksVerified | 35.3 | 5 benchmarks | Verified | |||
| ReasoningRank Not rankedWeight 17%2 benchmarksVerified | 43.7 | 2 benchmarks | Verified | |||
| MultimodalRank #29 of 58Percentile 51stWeight 12%2 benchmarksVerified | 74.0 | 2 benchmarks | Verified | |||
| KnowledgeRank #77 of 179Percentile 57thWeight 12%5 benchmarksMixed sources | 50.5 | 5 benchmarks | Mixed sources | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingRank #30 of 157Percentile 81stWeight 5%Not listedUnlisted sources | 89.9 | Not listed | Unlisted sources | |||
| MathRank Not rankedWeight 5%2 benchmarksVerified | 55.9 | 2 benchmarks | Verified |
22 of 782 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow 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.
- Agentic6/6 verified
- Coding5/5 verified
- Reasoning2/2 verified
- Multimodal2/2 verified
- Knowledge4/5 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- Math2/2 verified
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 mini category percentile values
- Agentic38th percentile
- Coding49th percentile
- ReasoningNot eligible
- Multimodal51st percentile
- Knowledge57th percentile
- MultilingualNot eligible
- Instruction following81st percentile
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#84/135
- Coding#80/156
- ReasoningNot ranked
- Multimodal#29/58
- Knowledge#77/179
- MultilingualNot ranked
- Inst. Following#30/157
- MathNot ranked
Benchmark ledger
Coding 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.
Coding5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| LiveCodeBench (Vals)LiveCodeBench, Vals AI run | Score81.5% | Versus best verified row Best verified: Claude Fable 5.1 · 90.5% | Gap9 behind | Weight8% ref. weight | |
| FrontierCode 1.1 Main | Score27.0% | Versus best verified row Best verified: Claude Opus 5.5 · 54.4% | Gap27.4 behind | Weight4% ref. weight | Benchmark exact |
| Terminal-Bench 2.0 | Score60.0% | Versus best verified row Best verified: GPT-5.5 · 82.0% | Gap22 behind | WeightScored in Agentic | Provider exact |
| Vibe Code BenchVibe Code Bench v1.1 | Score47.97% | Versus best verified row Best verified: Gemini 4 Argon · 91.90% | Gap43.9 behind | WeightDisplay only | Benchmark exact |
| SWE-bench (Vals)SWE-bench, Vals AI run | Score73.0% | Versus best verified row Best verified: Claude Opus 5 · 97.0% | Gap24 behind | WeightDisplay only | Verified |
Agentic6 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 2.0 | Score60% | Versus best verified row Best verified: GPT-5.5 · 82% | Gap22 behind | Weight7% ref. weight | Provider exact |
| OSWorld-Verified | Score72.1% | Versus best verified row Best verified: Qwen3.8 Max · 86.1% | Gap14 behind | Weight7% ref. weight | Provider exact |
| MCP Atlas | Score57.7% | Versus best verified row Best verified: Muse Spark Open · 89.2% | Gap31.5 behind | Weight4% ref. weight | Provider exact |
| Terminal-Bench 2.1 (Vals)Terminal-Bench 2.1, Vals AI run | Score54.7% | Versus best verified row Best verified: GPT-6 Astra · 87.3% | Gap32.6 behind | Weight4% ref. weight | |
| Toolathlon | Score42.9% | Versus best verified row Best verified: Muse Spark 1.1 · 75.6% | Gap32.7 behind | Weight3% ref. weight | Provider exact |
| τ²-bench resultsτ²-Bench Tool-Agent-User Evaluation | Score93.4% | Versus best verified row Best verified: GPT-5.4 · 98.9% | Gap5.5 behind | WeightDisplay only | Provider exact |
Reasoning2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ARC-AGI-2Abstraction and Reasoning Corpus for AGI v2 | Score18.9% | Versus best verified row Best verified: GPT-6 Astra · 95% | Gap76.1 behind | WeightWeighted 25% | Benchmark exact |
| ARC-AGI-1ARC-AGI-1 Semi-Private Evaluation | Score63.70% | Versus best verified row Best verified: Claude Fable 5 · 98.50% | Gap34.8 behind | WeightDisplay only | Benchmark exact |
Multimodal2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | Score76.6% | Versus best verified row Best verified: GPT-6.1 Terra · 85.5% | Gap8.9 behind | WeightWeighted 40% | Provider exact |
| MMMU-Pro w/ PythonMMMU-Pro with Python | Score78% | Versus best verified row Best verified: Kimi K3.1 Pro · 90% | Gap12 behind | WeightDisplay only | Provider exact |
Knowledge5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HLEHumanity's Last Exam | Score41.5% | Versus best verified row Best verified: Kimi K3.1 Pro · 70% | Gap28.5 behind | Weight44% ref. weight | Provider exact |
| HLE w/o toolsHumanity's Last Exam without tools | Score28.2% | Versus best verified row Best verified: Claude Opus 5.5 · 64.4% | Gap36.2 behind | Weight7% ref. weight | Provider exact |
| MMLU-Pro (Vals)MMLU-Pro, Vals AI run | Score84.6% | Versus best verified row Best verified: Claude Fable 5.1 · 92.4% | Gap7.8 behind | Weight6% ref. weight | Verified |
| GPQAGraduate-Level Google-Proof Q&A | Score88% | Versus best verified row Best verified: GPT-6 Astra · 96% | Gap8 behind | Weight3% ref. weight | Reported |
| GPQA Diamond (Vals)GPQA Diamond, Vals AI run | Score83.1% | Versus best verified row Best verified: Gemini 3.1 Pro · 95.5% | Gap12.4 behind | Weight2% ref. weight |
Math2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| FrontierMath v2 (Tiers 1-3)FrontierMath v2 Tiers 1-3 | Score51.228% | Versus best verified row Best verified: GPT-6 Astra · 93.684% | Gap42.5 behind | WeightWeighted 30% | Benchmark exact |
| FrontierMath v2 (Tier 4)FrontierMath v2 Tier 4 | Score9.756% | Versus best verified row Best verified: GPT-6.1 Sol · 100.000% | Gap90.2 behind | WeightWeighted 10% | Benchmark exact |
Bars run 0–100; the dark tick marks the best source-verified value
All 22 rowsWhat 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.
GPT-5.4 mini · 53.0 score · $2.63 blended per million tokens
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Horizontal: blended price per million tokens, log scale · Vertical: public score
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
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-miniOpenAI GPT-5.4 mini model documentation
- Context window
- 400KOpenAI GPT-5.4 mini 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 mini model documentation
- API capabilities
- Tool calling, structured outputs, and batch support are not tracked yet
- Prompt caching
- Published at $0.075 per million cached input tokensOpenAI pricing
- Self-host
- Weights are not published
- Rate limits
- Not tracked yet
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 mini ranks #90 of 216 on the public leaderboard with a score of 52.98/100. Its source-verified position is #45 of 77.
GPT-5.4 mini is a proprietary model with a 400K context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
GPT-5.4 mini sits in the GPT-5.4 family with GPT-5.4, GPT-5.4 nano, GPT-5.4 Pro. Its explicit predecessor is GPT-5 mini. 22 of 782 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multimodal & Grounded at #29, while its lowest eligible position is Agentic at #84. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Last updated October 29, 2026. Runtime fields remain blank until a sourced snapshot exists.
Deployment options
Self-host and provider-specific paths stay separate from benchmark evidence so operating constraints are visible before a score becomes the whole decision.
Where to run GPT-5.4 mini by API
OpenRouter is the one host we track that publishes a per-token price for it. Prices read from each host’s own pages on October 20, 2026.
| Host | Input /1M | Output /1M | Cached /1M | Context |
|---|---|---|---|---|
| OpenRouter | $0.75 | $4.50 | $0.075 | 400K |
Questions
How does GPT-5.4 mini perform overall in AI benchmarks?
GPT-5.4 mini ranks #90 out of 216 models on the public BenchAlign leaderboard, with a score of 52.98/100. Its evidence status is Supported, and this profile shows 22 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 mini good for knowledge and understanding?
GPT-5.4 mini ranks #77 out of 179 eligible models for knowledge and understanding, with a public category score of 50.5/100. 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 mini good for coding and programming?
GPT-5.4 mini ranks #80 out of 156 eligible models for coding and programming, with a public category score of 35.3/100. 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 mini good for mathematics?
GPT-5.4 mini 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 mini good for reasoning and logic?
GPT-5.4 mini 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 mini good for agentic tool use and computer tasks?
GPT-5.4 mini ranks #84 out of 135 eligible models for agentic tool use and computer tasks, with a public category score of 36.4/100. 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 mini good for multimodal and grounded tasks?
GPT-5.4 mini ranks #29 out of 58 eligible models for multimodal and grounded tasks, with a public category score of 74/100. 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 mini?
GPT-5.4 mini belongs to the GPT-5.4 family. Related tracked variants include GPT-5.4, GPT-5.4 nano, GPT-5.4 Pro. 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 mini have full benchmark coverage on BenchLM?
No. GPT-5.4 mini currently has 41 source-displayable rows. 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 mini?
GPT-5.4 mini has a documented context window of 400K. 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.