Skip to main content
BenchLM
Advertise

Model comparison

GPT-5.4 vs GPT-5.4 mini

Updated August 1, 2026. Public scores include evidence status and uncertainty. They are not guarantees for a specific workload. This is a same-family comparison, so migration details appear when the source data supports them.

20 confirmed releases in the last 30 daysGet OpenAI alerts · $4.99/monthPaid subscription · no free trial
GPT-5.4

OpenAI

73.2/100

Supported · Public rank #10

90% interval 70.3–76.2

GPT-5.4 mini

OpenAI

55.8/100

Estimated · Public rank #82

90% interval 44.3–67.3

GPT-5.4 has the higher public score, 73.24 versus 55.82, and the 90% score intervals do not overlap.

13 results are shared. Category rows based on different benchmark sets are marked directional and do not name a winner.

Which one for your work

Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.

  • Long documents

    Prompts that approach the documented context limit

    GPT-5.4

    GPT-5.4 has the larger documented context window.

    Confidence: documented

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-5.4 mini

    GPT-5.4 mini has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Cache-heavy agent loop cost

    200K cached + 20K fresh input + 10K output tokens

    GPT-5.4 mini

    GPT-5.4 mini has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

Show secondary and unsupported calls

  • Repository review cost

    50K fresh input + 3K output tokens

    GPT-5.4 mini

    GPT-5.4 mini has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.

    Confidence: listed-rates

  • Coding work

    Code generation, repair, and software-engineering tasks

    Not enough matched evidence

    No shared weighted benchmark basis supports a winner.

    Confidence: limited

  • Agentic work

    Tool use, computer use, and multi-step task completion

    Not enough matched evidence

    The category averages use different weighted benchmark sets, so they are directional rather than like-for-like.

    Confidence: limited

What is actually comparable

Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.

Shared results
13
GPT-5.4 only
24
GPT-5.4 mini only
1
Like-for-like categories
2 / 8

2 categories use different evidence sets. Those rows remain visible for coverage context but do not name a winner.

Category results, on a stated basis

Each row states whether both averages use the same weighted benchmark set. Directional and not-comparable rows remain visible, but they never receive a winner in this template.

Knowledge

Like-for-like
GPT-5.4
57.6
GPT-5.4 mini
47.8
Weighted basis
2 vs 2 rows
Reading
GPT-5.4 leads

Math

Like-for-like
GPT-5.4
42.5
GPT-5.4 mini
21.7
Weighted basis
2 vs 2 rows
Reading
GPT-5.4 leads

Agentic

Directional only
GPT-5.4
77.2
GPT-5.4 mini
65.7
Weighted basis
3 vs 2 rows
Reading
Directional only

Multimodal

Directional only
GPT-5.4
73.2
GPT-5.4 mini
76.6
Weighted basis
3 vs 1 rows
Reading
Directional only

Coding

Not comparable
GPT-5.4
57.7
GPT-5.4 mini
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Reasoning

Not comparable
GPT-5.4
74.0
GPT-5.4 mini
Not measured
Weighted basis
1 vs 0 rows
Reading
Not comparable

Multilingual

Not comparable
GPT-5.4
Not measured
GPT-5.4 mini
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Instruction following

Not comparable
GPT-5.4
Not measured
GPT-5.4 mini
Not measured
Weighted basis
0 vs 0 rows
Reading
Not comparable

Shape of the matched evidence

Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.

Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.

What each workload costs

Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.

Chat turn

1K fresh input + 500 output tokens

GPT-5.4
$0.01
Fits in one request
GPT-5.4 mini
$0.003
Fits in one request

GPT-5.4 mini has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-5.4
$0.17
Fits in one request
GPT-5.4 mini
$0.051
Fits in one request

GPT-5.4 mini has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

GPT-5.4
$0.25
Fits in one request
GPT-5.4 mini
$0.075
Fits in one request

GPT-5.4 mini has the lower modeled cost

Costs use the listed standard API rates.

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

GPT-5.4

$0.25 per 1M cached input tokens

OpenAI pricing

GPT-5.4 mini

$0.075 per 1M cached input tokens

OpenAI pricing

Provider availability

GPT-5.4

Not sourced

GPT-5.4 mini

Generally Available · OpenAI Responses API

OpenAI model catalog

Reasoning profile

GPT-5.4

Reasoning

GPT-5.4 mini

Reasoning

Weight access

GPT-5.4

Proprietary

GPT-5.4 mini

Proprietary

License

GPT-5.4

Proprietary

GPT-5.4 mini

Proprietary

Release date

GPT-5.4

2026-03-05

GPT-5.4 mini

2026-03-17

If you are choosing between sibling variants
Deployment change
Both entries list OpenAI as the provider. Confirm endpoint, model ID, limits, and feature support before switching.
Quality signal
GPT-5.4 has the higher public score, 73.24 versus 55.82, and the 90% score intervals do not overlap.
Workload cost
Repository review: $0.17 vs $0.051. Cache-heavy agent loop: $0.25 vs $0.075.
Context tradeoff
GPT-5.4 has the larger documented window (1.05M).

Run the same representative tasks against both endpoints before changing production traffic.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence38 rows

Agentic

  • Terminal-Bench 2.0

    GPT-5.475.1%
    Source
    GPT-5.4 mini60%
    Source

    GPT-5.4 leads this result

  • CyberGym

    GPT-5.479.0%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • BrowseComp

    GPT-5.482.7%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • OSWorld-Verified

    GPT-5.475%
    Source
    GPT-5.4 mini72.1%
    Source

    GPT-5.4 leads this result

  • MCP Atlas

    GPT-5.470.6%
    Source
    GPT-5.4 mini57.7%
    Source

    GPT-5.4 leads this result

  • Toolathlon

    GPT-5.454.6%
    Source
    GPT-5.4 mini42.9%
    Source

    GPT-5.4 leads this result

  • τ²-bench results

    Shared source
    GPT-5.498.9%
    GPT-5.4 mini93.4%

    GPT-5.4 leads this result

  • Claw-Eval

    GPT-5.460.3%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • DeepSearchQA

    GPT-5.473.6%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • Gert Labs

    GPT-5.464.89%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • ResearchClawBench

    GPT-5.415.3%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • JobBench

    GPT-5.438.9%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • ExploitGym

    GPT-5.46.0%
    Source
    GPT-5.4 mini—

    Not directly comparable

Coding

  • LiveCodeBench Pro

    GPT-5.487.5%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • SWE-bench Pro

    GPT-5.457.7%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • React Native Evals

    GPT-5.485.3%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • Vibe Code Bench

    Shared source
    GPT-5.467.42%
    GPT-5.4 mini47.97%

    GPT-5.4 leads this result

  • FrontierCode 1.1 Main

    GPT-5.4—
    GPT-5.4 mini27.0%
    Source

    Not directly comparable

Reasoning

  • ARC-AGI-2

    GPT-5.474.0%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • ARC-AGI-3

    GPT-5.40.2%
    Source
    GPT-5.4 mini—

    Not directly comparable

Knowledge

  • GPQA

    GPT-5.492.8%
    Source
    GPT-5.4 mini88%
    Source

    GPT-5.4 leads this result

  • HLE

    GPT-5.452.1%
    Source
    GPT-5.4 mini41.5%
    Source

    GPT-5.4 leads this result

  • HLE w/o tools

    GPT-5.439.8%
    Source
    GPT-5.4 mini28.2%
    Source

    GPT-5.4 leads this result

  • GPQA-D

    GPT-5.492.8%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • HealthBench Hard

    GPT-5.440.1%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • MedXpertQA (Text)

    GPT-5.459.6%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • HealthBench Professional

    GPT-5.448.1%
    Source
    GPT-5.4 mini—

    Not directly comparable

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    GPT-5.447.600%
    GPT-5.4 mini28.280%

    GPT-5.4 leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    GPT-5.427.100%
    GPT-5.4 mini2.080%

    GPT-5.4 leads this result

Multimodal

  • MMMU-Pro

    GPT-5.481.2%
    Source
    GPT-5.4 mini76.6%
    Source

    GPT-5.4 leads this result

  • OfficeQA Pro

    GPT-5.453.2%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • MMMU-Pro w/ Python

    GPT-5.482.1%
    Source
    GPT-5.4 mini78%
    Source

    GPT-5.4 leads this result

  • CharXiv

    GPT-5.482.8%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • ERQA

    GPT-5.465.4%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • SimpleVQA

    GPT-5.461.1%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • ScreenSpot Pro

    GPT-5.485.4%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • ZeroBench

    GPT-5.441.0%
    Source
    GPT-5.4 mini—

    Not directly comparable

  • MedXpertQA (MM)

    GPT-5.477.1%
    Source
    GPT-5.4 mini—

    Not directly comparable

Frequently asked questions

Which is better, GPT-5.4 or GPT-5.4 mini?

GPT-5.4 has the higher public score, 73.24 versus 55.82, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.

Which is better for coding, GPT-5.4 or GPT-5.4 mini?

The published evidence does not provide a shared weighted coding basis for both models, so BenchLM does not name a coding winner.

Which is better for agentic tasks, GPT-5.4 or GPT-5.4 mini?

The current agentic tasks averages use different weighted benchmark sets, so BenchLM does not name a winner from them. Read the shared benchmark rows directly and test the models on the same task set.

Which costs less, GPT-5.4 or GPT-5.4 mini?

For the stated presets, chat costs $0.01 on GPT-5.4 and $0.003 on GPT-5.4 mini; repository review costs $0.17 and $0.051; the cache-heavy agent loop costs $0.25 and $0.075. Costs use the listed standard API rates.

Which has the larger context window, GPT-5.4 or GPT-5.4 mini?

GPT-5.4 has the larger documented context window: 1.05M, compared with 400K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated August 1, 2026

Watch GPT-5.4 vs GPT-5.4 mini

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 2,000+ readers.