Skip to main content
BenchLM
Advertise

Model comparison

GPT-5.4 mini vs GPT-5.4 nano

Updated July 31, 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.

GPT-5.4 mini

OpenAI

55.8/100

Estimated · Public rank #82

90% interval 44.3–67.3

GPT-5.4 nano

OpenAI

66.0/100

Supported · Public rank #28

90% interval 55.5–76.5

GPT-5.4 nano has the higher public score estimate, 65.99 versus 55.84, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.

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.

  • Agentic work

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

    GPT-5.4 mini

    GPT-5.4 mini leads on the same 2 weighted benchmark rows.

    Confidence: limited

  • Chat turn cost

    1K fresh input + 500 output tokens

    GPT-5.4 nano

    GPT-5.4 nano 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 nano

    GPT-5.4 nano 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 nano

    GPT-5.4 nano 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

  • Long documents

    Prompts that approach the documented context limit

    No clear pick

    The documented context windows are equal.

    Confidence: documented

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 mini only
1
GPT-5.4 nano only
0
Like-for-like categories
4 / 8

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.

Agentic

Like-for-like
GPT-5.4 mini
65.7
GPT-5.4 nano
42.9
Weighted basis
2 vs 2 rows
Reading
GPT-5.4 mini leads

Knowledge

Like-for-like
GPT-5.4 mini
47.8
GPT-5.4 nano
43.8
Weighted basis
2 vs 2 rows
Reading
GPT-5.4 mini leads

Math

Like-for-like
GPT-5.4 mini
21.7
GPT-5.4 nano
21.0
Weighted basis
2 vs 2 rows
Reading
GPT-5.4 mini leads

Multimodal

Like-for-like
GPT-5.4 mini
76.6
GPT-5.4 nano
66.1
Weighted basis
1 vs 1 rows
Reading
GPT-5.4 mini leads

Coding

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

Reasoning

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

Multilingual

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

Instruction following

Not comparable
GPT-5.4 mini
Not measured
GPT-5.4 nano
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.

  • OSWorld-Verified

    Agentic

    GPT-5.4 mini: 72.1%GPT-5.4 nano: 39%Normalized gap 33.1Shared source

  • Terminal-Bench 2.0

    Agentic

    GPT-5.4 mini: 60%GPT-5.4 nano: 46.3%Normalized gap 13.7Shared source

  • MMMU-Pro

    Multimodal

    GPT-5.4 mini: 76.6%GPT-5.4 nano: 66.1%Normalized gap 10.5Shared source

  • GPQA

    Knowledge

    GPT-5.4 mini: 88%GPT-5.4 nano: 82.8%Normalized gap 5.2Shared source

  • FrontierMath v2 (Tier 4)

    Math

    GPT-5.4 mini: 2.080%GPT-5.4 nano: 6.250%Normalized gap 4.2Shared source

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 mini
$0.003
Fits in one request
GPT-5.4 nano
$0.00082
Fits in one request

GPT-5.4 nano has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-5.4 mini
$0.051
Fits in one request
GPT-5.4 nano
$0.01375
Fits in one request

GPT-5.4 nano 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 mini
$0.075
Fits in one request
GPT-5.4 nano
$0.0205
Fits in one request

GPT-5.4 nano 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 mini

$0.075 per 1M cached input tokens

OpenAI pricing

GPT-5.4 nano

$0.02 per 1M cached input tokens

OpenAI pricing

Reasoning profile

GPT-5.4 mini

Reasoning

GPT-5.4 nano

Reasoning

Weight access

GPT-5.4 mini

Proprietary

GPT-5.4 nano

Proprietary

License

GPT-5.4 mini

Proprietary

GPT-5.4 nano

Proprietary

Release date

GPT-5.4 mini

2026-03-17

GPT-5.4 nano

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 nano has the higher public score estimate, 65.99 versus 55.84, but the 90% score intervals overlap.
Workload cost
Repository review: $0.051 vs $0.01375. Cache-heavy agent loop: $0.075 vs $0.0205.
Context tradeoff
Both models list 400K.

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 evidence14 rows

Agentic

  • Terminal-Bench 2.0

    Shared source
    GPT-5.4 mini60%
    GPT-5.4 nano46.3%

    GPT-5.4 mini leads this result

  • OSWorld-Verified

    Shared source
    GPT-5.4 mini72.1%
    GPT-5.4 nano39%

    GPT-5.4 mini leads this result

  • MCP Atlas

    Shared source
    GPT-5.4 mini57.7%
    GPT-5.4 nano56.1%

    GPT-5.4 mini leads this result

  • Toolathlon

    Shared source
    GPT-5.4 mini42.9%
    GPT-5.4 nano35.5%

    GPT-5.4 mini leads this result

  • τ²-bench results

    Shared source
    GPT-5.4 mini93.4%
    GPT-5.4 nano92.5%

    GPT-5.4 mini leads this result

Coding

  • Vibe Code Bench

    Shared source
    GPT-5.4 mini47.97%
    GPT-5.4 nano26.10%

    GPT-5.4 mini leads this result

  • FrontierCode 1.1 Main

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

    Not directly comparable

Knowledge

  • GPQA

    Shared source
    GPT-5.4 mini88%
    GPT-5.4 nano82.8%

    GPT-5.4 mini leads this result

  • HLE

    Shared source
    GPT-5.4 mini41.5%
    GPT-5.4 nano37.7%

    GPT-5.4 mini leads this result

  • HLE w/o tools

    Shared source
    GPT-5.4 mini28.2%
    GPT-5.4 nano24.3%

    GPT-5.4 mini leads this result

Math

  • FrontierMath v2 (Tiers 1-3)

    Shared source
    GPT-5.4 mini28.280%
    GPT-5.4 nano25.860%

    GPT-5.4 mini leads this result

  • FrontierMath v2 (Tier 4)

    Shared source
    GPT-5.4 mini2.080%
    GPT-5.4 nano6.250%

    GPT-5.4 nano leads this result

Multimodal

  • MMMU-Pro

    Shared source
    GPT-5.4 mini76.6%
    GPT-5.4 nano66.1%

    GPT-5.4 mini leads this result

  • MMMU-Pro w/ Python

    Shared source
    GPT-5.4 mini78%
    GPT-5.4 nano69.5%

    GPT-5.4 mini leads this result

Frequently asked questions

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

GPT-5.4 nano has the higher public score estimate, 65.99 versus 55.84, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

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

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 mini or GPT-5.4 nano?

GPT-5.4 mini leads the like-for-like agentic tasks comparison across 2 shared weighted benchmark rows.

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

For the stated presets, chat costs $0.003 on GPT-5.4 mini and $0.00082 on GPT-5.4 nano; repository review costs $0.051 and $0.01375; the cache-heavy agent loop costs $0.075 and $0.0205. Costs use the listed standard API rates.

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

Both models list the same context window, 400K.

Related comparisons

Compare API pricing Read the methodology Open the model selector

Last updated July 31, 2026

Watch GPT-5.4 mini vs GPT-5.4 nano

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

Read a sample issue

Join 2,000+ readers.